- %TI Proceedings of the 1992 Cognitive Science Graduate Student Conference
- %AU T. Simon (ed.)
- %PU Technical Report GIT-CS-92/01, Cognitive Science Program, College of
Computing, Georgia Institute of Technology, Atlanta, GA, 1992
- %AV mailto:cogsci-secretary@cc.gatech.edu
- %OR GTECH
- %LT GIT-CS-92/01
- %YR 1992
- %TI Introspective Multistrategy Learning
- %AU Michael T. Cox
- %PU Technical Report GIT-CS-93/02, Cognitive Science Program, College of
Computing, Georgia Institute of Technology, Atlanta, GA, 1993
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cs-93-02.ps.Z
- %OR GTECH
- %LT GIT-CS-93/02
- %YR 1993
- %AB The thesis of this proposal is that introspection facilitates
learning by providing a basis for identifying what needs to be
learned and for selecting an appropriate learning algorithm. If the
system has a model of its own reasoning processes and of the
knowledge used by these reasoning processes, it can declaratively
represent the events and causal relations in the mental world in the
same manner that it represents events and relations in the physical
world. A multistrategy learning system, in which several learning
algorithms are available, can decide what to learn, and which
algorithm(s) to apply, by analyzing this model of its reasoning.
This introspective analysis allows it to understand its reasoning
failures, to determine the causes of the failures, to identify
needed knowledge repairs in order to avoid such failures in the
future, and to select the learning algorithm appropriate for the
needed repairs. Thus, the object of the proposed research is to
develop both a content theory and a process theory of introspective
multistrategy learning and to establish the conditions under which
such an approach is fruitful.
- %TI Proceedings of the 1993 Cognitive Science Graduate Student Conference
- %AU D. Billman (ed.)
- %PU Technical Report GIT-CS-93/03, Cognitive Science Program, College of
Computing, Georgia Institute of Technology, Atlanta, GA, 1993
- %AV mailto:cogsci-secretary@cc.gatech.edu
- %OR GTECH
- %LT GIT-CS-93/03
- %YR 1993
- %TI Proceedings of the 1994 Cognitive Science Graduate Student Conference
- %AU M.T. Cox, A. Cabrera, A. Edmonds, K. Moorman, & J. Sawyer (eds.)
- %PU Technical Report GIT-CS-94/04, Cognitive Science Program, College of
Computing, Georgia Institute of Technology, Atlanta, GA, 1994
- %AV mailto:cogsci-secretary@cc.gatech.edu
- %OR GTECH
- %LT GIT-CS-94/04
- %YR 1994
- %TI Learning to Learn
- %AU Angel Cabrera
- %PU Technical Report GIT-CS-94/05, Cognitive Science Program, College of
Computing, Georgia Institute of Technology, Atlanta, GA, 1994
- %AV mailto:angel@psy.gatech.edu
- %OR GTECH
- %LT GIT-CS-94/05
- %YR 1994
- %AB This paper reviews various literature sources dealing with animal,
human and machine "learning-to-learn" or learning transfer.
Learning to learn is defined as the effect of a learning experience
in future learning efficiency. From the learning framework common
in the machine learning arena, learning to learn can be viewed as an
adaptation and creation of learning biases based on learning
experience. Organisms have innate capacity for learning in a broad
class of domains. As organisms interact with a particular
environment, they get to develop stronger learning biases that
render future learning more efficient given that certain
characteristics of the environment remain relatively stable.
Animals can learn to learn by specializing in particular perceptual
features and by developing pre-generalization classes or categories.
Humans can do that and more. In particular, they are able to
develop domain theories that guide future learning. Machine models
have been developed that touch, to some extent, all those modalities
of learning to learn. However, not much effort has been invested in
formalizing this ability.
- %TI Deciphering "Jabberwocky": Contributions from Language to Event
Categorization
- %AU Angel Cabrera and Dorrit Billman
- %PU Technical Report GIT-CS-94/06, Cognitive Science Program, College of
Computing, Georgia Institute of Technology, Atlanta, GA, 1994
- %AV mailto:angel@psy.gatech.edu
- %OR GTECH
- %LT GIT-CS-94/06
- %YR 1994
- %AB This work explores the role that language plays in the acquisition
of event categories. Subjects were presented with computer animated
scenes each preceded by an English-like spoken utterance that used
novel nouns and verbs. We manipulated the lexical and syntactic
forms in the sentences and the mappings between these aspects of
language and the scenes. The three experiments reported here showed
that the systematic variation of some aspect of language with the
scenes significantly facilitated the learning of the nonlinguistic
regularities of the events. Experiment 1 showed that combining
lexical and argument structure variations facilitated event learning
more than lexical information alone. Experiment 2 showed a benefit
from lexical variations and from variations in preposition of the
verbUs argument, but no increased benefit from providing both
sources of information. This pattern of results held even when the
prepositions were assigned to the events in a way that conflicted
with normal English use. Experiment 3 confirmed the contrast
between Experiments 1 and 2: combining lexical and argument
structure variations had a stronger beneficial effect on learning
that having only lexical variations. But combining lexical with
prepositional manipulations did not provide additional benefit.
These results have implications concerning theories about the
relationship between language and thought and theories of category
acquisition. An extended version of the Whorfian hypothesis is
supported: language may have a privileged effect on the process of
learning event categories. This role of language, it is argued, may
contradict predictions from prior theories of category acquisition
that claim a universal facilitative effect of increased information
redundancy in the input. Interferences among different aspects of
language indicate that the role of language in category formation
may be more complicated than initially expected.
- %TI Improving Examples to Improve Transfer to Novel Problems
- %AU Richard Catrambone
- %PU Technical Report GIT-CS-94/07, Cognitive Science Program, School of
Psychology, Georgia Institute of Technology, Atlanta, GA, 1994
- %AV mailto:richard.catrambone@psych.gatech.edu
- %OR GTECH
- %LT GIT-CS-94/07
- %YR 1994
- %AB People often memorize a set of steps for solving problems when they
study worked-out examples in domains such as math and physics
without learning what domain-relevant subgoals or subtasks these
steps achieve. As a result, they have trouble solving novel
problems that contain the same structural elements but require
different lower-level steps. In three experiments, subjects who
studied example solutions that emphasized a needed subgoal were more
likely to solve novel problems that required a new approach for
achieving this subgoal than subjects who did not learn this subgoal.
This result suggests that research aimed at determining the factors
that influence subgoal learning may be valuable in improving
transfer from examples to novel problems.
- %TI Aiding Subgoal Learning: Effects on Transfer
- %AU Richard Catrambone
- %PU Technical Report GIT-CS-94/08, Cognitive Science Program, School of
Psychology, Georgia Institute of Technology, Atlanta, GA, 1994
- %AV mailto:richard.catrambone@psych.gatech.edu
- %OR GTECH
- %LT GIT-CS-94/08
- %YR 1994
- %AB Students often memorize a set of steps from examples in domains such
as probability and physics, without learning what subgoals those
steps achieve. A result of this sort of learning can be that these
students fail to solve novel problems that do not permit exactly the
same set of steps even though the old goal structure is maintained.
Three experiments demonstrated that both labeling and visually
isolating a set of steps in examples would independently help
students learn a subgoal and thus, be more likely to solve novel
problems that involve that subgoal but require different steps to
achieve it.
- %TI Metacognition, Problem Solving and Aging
- %AU Michael T. Cox
- %PU Technical Report GIT-CS-94/15, Cognitive Science Program, College of
Computing, Georgia Institute of Technology, Atlanta, GA, 1994
- %AV ftp://ftp.cc.gatech.edu/pub/ai/students/cox/Papers/metacognition-tech-rep.ps.Z
- %OR GTECH
- %LT GIT-CS-94/15
- %YR 1994
- %AB Although much of cognition is certainly a function of memory, analysis of
metacognition in the context of cognitive aging research should include
higher cognitive processes such as problem solving and comprehension,
rather than limiting itself to basic memory-phenomena. A literature
review shows that research has investigated cognitive aging and problem
solving, aging and metacognition, and metacognition and problem
solving. Yet, no studies examine the relationship between metacognition
and problem solving as a function of age. This paper suggests a simple
modification to an existing non-aging paradigm that applies it to aging
research in order to begin to close this gap. Such approaches, however,
are fraught with difficulties, both conceptual and methodological. For
example, a conceptual separation should be made between subjects'
reasoning concerning the problem itself and their reasoning about the
solving of the problem, yet methodologically there exists no general
empirical procedure for separating knowledge of performance and knowledge
of thinking about performance. An additional difficulty is the problem of
distinguishing between mental processes and mental states --between
transformations and the knowledge that is transformed. To begin to
address some of these issues, this paper borrows some ideas from both the
artificial intelligence and metacognition literatures in order to outline
a taxonomy of ontological categories that targets the distinction between
metacognitive and cognitive knowledge.
- %TI The Convergence of Explanatory Coherence and the Story Model: A Case
Study in Juror Decision
- %AU Michael D. Byrne
- %PU Technical Report GIT-CS-94/18, Cognitive Science Program, School of
Psychology, Georgia Institute of Technology, Atlanta, GA 1994
- %AV ftp://ftp.cc.gatech.edu/pub/people/byrne/git-cs-94-18.ps.Z
- %OR GTECH
- %LT GIT-CS-94/18
- %YR 1994
- %AB This paper presents an integration of two approaches to complex
decision-making from very different traditions: from the psychology
of jury decision, the Story Model, and from the philosophy of
science, the Theory of Explanatory Coherence and its computational
instantiation, ECHO. The subjects in Pennington & Hastie (1993)
generated causal "stories" to represent the events related to a
particular trial. These stories were modeled with ECHO, and ECHO
reached the same verdicts as did the human subjects. The ECHO
simulations were also linked to the trial testimony, which, despite
the inconsistent nature of the testimony, actually increased the
coherence of stories for two jurors with very different
verdicts. Implications for both the Story Model and ECHO are
discussed.
- %TI Having Your Cake and Eating It Too: Autonomy and Interaction in a Model
of Sentence Processing
- %AU Kurt P. Eiselt
- %AU Kavi Mahesh
- %AU Jennifer K. Holbrook
- %PU AAAI-93: Proceedings of the Eleventh National Conference on Artificial
Intelligence
- %AV ftp ftp.cc.gatech.edu:/pub/ai/eiselt/er-km-93-01.ps.Z
- %OR GTECH
- %LT ER-KM-93/01
- %YR 1993
- %AB Is the human language understander a collection of modular processes
operating with relative autonomy, or is it a single integrated process?
This ongoing debate has polarized the language processing community, with
two fundamentally different types of model posited, and with each camp
concluding that the other is wrong. One camp puts forth a model with
separate processors and distinct knowledge sources to explain one body of
data, and the other proposes a model with a single processor and a
homogeneous, monolithic knowledge source to explain the other body of
data. In this paper we argue that a hybrid approach which combines a
unified processor with separate knowledge sources provides an explanation
of both bodies of data, and we demonstrate the feasibility of this
approach with the computational model called COMPERE. We believe that
this approach brings the language processing community significantly
closer to offering human-like language processing systems.
- %TI A Unified Process Model of Syntactic and Semantic Error Recovery in
Sentence Understanding
- %AU Jennifer K. Holbrook
- %AU Kurt P. Eiselt
- %AU Kavi Mahesh
- %PU Cogsci-92: In Proceedings of the Fourteenth Annual Conference of the
Cognitive Science Society
- %AV ftp ftp.cc.gatech.edu:/pub/ai/eiselt/er-km-92-01.ps.Z
- %OR GTECH
- %LT ER-KM-92/01
- %YR 1992
- %AB The development of models of human sentence processing has traditionally
followed one of two paths. Either the model posited a sequence of
processing modules, each with its own task-specific knowledge (e.g.,
syntax and semantics), or it posited a single processor utilizing
different types of knowledge inextricably integrated into a monolithic
knowledge base. Our previous work in modeling the sentence processor
resulted in a model in which different processing modules used separate
knowledge sources but operated in parallel to arrive at the
interpretation of a sentence. One highlight of this model is that it
offered an explanation of how the sentence processor might recover from
an error in choosing the meaning of an ambiguous word: the semantic
processor briefly pursued the different interpretations associated with
the different meanings of the word in question until additional text
confirmed one of them, or until processing limitations were exceeded.
Errors in syntactic ambiguity resolution were assumed to be handled in
some other way by a separate syntactic module. Recent experimental work
by Laurie Stowe strongly suggests that the human sentence processor deals
with syntactic error recovery using a mechanism very much like that
proposed by our model of semantic error recovery. Another way to
interpret Stowe's finding that two significantly different kinds of
errors are handled in the same way is this: the human sentence processor
consists of a single unified processing module utilizing multiple
independent knowledge sources in parallel. A sentence processor built
upon this architecture should at times exhibit behavior associated with
modular approaches, and at other times act like an integrated system. In
this paper we explore some of these ideas via a prototype computational
model of sentence processing called COMPERE, and propose a set of
psychological experiments for testing our theories.
- %TI KA: Integrating natural language understanding with design problem
solving
- %AU Kavi Mahesh
- %AU Justin Peterson
- %AU Ashok Goel
- %AU Kurt P. Eiselt
- %PU In Working Notes from the AAAI Spring Symposium on Active NLP: Natural
Language Understanding in Integrated Systems
- %AV ftp ftp.cc.gatech.edu:/pub/ai/eiselt/er-km-94-01.ps.Z
- %OR GTECH
- %LT ER-KM-94/01
- %YR 1994
- %AB In this article, we present our research on the integration of natural
language understanding and problem solving capabilities in the context of
the design of physical devices. We describe an experimental integrated
system called KA [Goel and Eiselt, 1991; Pittges et al, 1993] that
illustrates some of the benefits of building an integrated theory of
multiple cognitive tasks focusing on language u nderstanding and its
interaction with design problem solving. We show for example how our work
on KA imposed constraints on the target representation of natural
language understanding and how the integrated approach redefined
classical problems in language processing such as ambiguity and
underspecification in terms of the overall goals of the KA system.
Language understanding imposed constraints, in return, on the task
structure of the design problem solver.
- %TI A Theory of Interaction and Independence in Sentence Understanding
- %AU Kavi Mahesh
- %PU College of Computing Technical Report, PhD Thesis Proposal.
- %AV ftp ftp.cc.gatech.edu:/pub/tech_reports/1993/GIT-CC-93-34.ps.Z
- %OR GTECH
- %LT GIT-CC-93/34
- %YR 1993
- %AB Developing a complete and well-specified computational model of human
language processing is a difficult problem. Natural language
understanding requires the application of many different kinds of
knowledge such as syntactic, semantic, and conceptual knowledge. To
account for the variety of constructs possible in natural languages and
to explain the variety of human behavior in sentence understanding, each
kind of knowledge must be applicable independently of others. However, in
order to efficiently resolve the many kinds of ambiguities that abound in
natural languages, the sentence processor must integrate information
available from different knowledge sources as soon as it can. Such early
commitment in ambiguity resolution calls for an ability to recover from
possible errors in commitment. In this work, we propose a
unified-process, multiple knowledge-source model of sentence
understanding that satisfies all the constraints above. In this model,
syntactic, semantic, and conceptual knowledge are represented separately
but in the same form. The single unified process utilizes all knowledge
sources to process a sentence. The unified process can resolve structural
as well as lexical ambiguities and recover from errors it might make. We
show that this model can account for a range of human sentence processing
behaviors by producing seemingly autonomous behavior at times and
interactive behaviors at other times. It is efficient since it supports
interaction between syntactic, semantic, and conceptual processing.
Moreover, the model aids portability between domains by separating
domain-specific knowledge from general linguistic knowledge. We also
present an early commitment, expectation-driven, bottom-up theory of
syntactic processing that permits us to unify syntactic processing with
semantic processing. We show several illustrative examples of ambiguity
resolution and error recovery processed by our prototype implementation
of the theory in a program called COMPERE (Cognitive Model of Parsing and
Error Recovery).
- %TI Student Strategies for Learning Programming from a Computational
Environment
- %AU Margaret Recker
- %AU Peter Pirolli
- %PU Proceedings of the International Conference on Intelligent Tutoring
- %AV ftp://ftp.cc.gatech.edu/pub/ai/mimi/er-mr-92-01.ps.Z
- %OR GTECH
- %LT ER-MR-92/01
- %YR 1992
- %AB This paper discusses the design and evaluation of a hypertext-based
environment that presents instructional material on programming in
Lisp. The design of the environment was motivated by results from
studies investigating students' strategies for knowledge acquisition.
The effectiveness of the design was evaluated by conducting a study
that investigated how subjects used and learned from the instructional
environment compared to subjects using more standard, structured,
linear instruction. The results showed an ability by
environment interaction: the higher ability subjects using the
hypertext environment improved and made significantly less errors when
programming new concepts while the lower ability subjects did not
improve and made more errors. Meanwhile, subjects using the control
environment did not show this ability-based difference. These results have
implications for the design of intelligent tutoring systems. They
affect decisions involving the amount of learner control that is
provided to students and the way student models are constructed.
- %TI Learning Strategies and Transfer in the Domain of Programming
- %AU Peter Pirolli
- %AU Margaret Recker
- %PU Cognition and Instruction, 12(3), 1994
- %AV ftp://ftp.cc.gatech.edu/pub/ai/mimi/er-mr-93-01.ps.Z
- %OR GTECH
- %LT ER-MR-93/01
- %YR 1994
- %AB We report two studies involving and intelligent tutoring system for
Lisp (the CMU Lisp Tutor). In Experiment 1, we develop a model,
based on production system theories of transfer and analogical
problem solving, that accounts for effects of instructional
examples, the transfer of cognitive skills across programming
problems, and practice effects. In Experiment 2, we analyzed
protocols collected from subjects as they processed instructional
texts and examples before working with the Lisp Tutor and protocols
collected after subjects solved each programming problem. The
results suggest that the acquisition of cognitive skills is
facilitated by high degrees of metacognition, which includes higher
degrees of monitoring states of knowledge, more self-generated
explanation goals and strategies, and greater attention to the
instructional structure. Improvement in skill acquisition is also
strongly related to the generation of explanations connecting the
example material to the abstract terms introduced in the text, the
generation of explanations that focus on the novel concepts, and
spending more time in planning solutions to novel task components.
We also found that self-explanation has diminishing returns.
Finally, reflection on problem solutions that focus on understanding
the abstractions underlying programs or that focus on understanding
how programs work, seems to be related to improved learning.
- %TI Modelling Individual Differences in Learning Strategies
- %AU Margaret Recker
- %AU Peter Pirolli
- %PU The Journal of the Learning Sciences, 4(1)
- %AV ftp://ftp.cc.gatech.edu/pub/ai/mimi/er-mr-93-02.ps.gz
- %OR GTECH
- %LT ER-MR-93/02
- %YR 1995
- %AB Learners employ a wide variety of strategies when faced with learning
and problem solving in a new domain. The focus of this research is on
learners' strategies when studying and explaining instructional
materials to themselves prior to problem solving. In the first part
of the paper, we present results from an empirical study in which
computer-based instructional situations were manipulated in order to
measure their effect on subjects' learning and self-explanation
strategies. We then present a Soar computational model that accounts
for results from the study. A particular emphasis of the model was on
capturing strategy differences between individual subjects. The
general modelling approach involved coupling a model of individual
subjects' interaction strategies with opportunities for action
supported by the interfaces of the instructional environments.
Specifically, by setting parameters, the model was fit to individual
subject data. Analyses of subjects' simulations contribute several
new results for understanding individual differences in strategy use
and their role in learning. We show that lower performing subjects
employed a high proportion of working memory intensive strategies,
which may have partially accounted for their inferior performance. In
addition, clusters of subjects identified through analyses of model
parameters continued to exhibit similar behaviors during subsequent
problem solving, suggesting that the clusters corresponded to genuine
strategy classes. Furthermore, these clusters appeared to represent
general strategies that were, in some sense, adaptive to the task.
- %TI Explorations in the Parameter Space of a Model Fit to
Individual Subjects' Strategies while Learning from Instructions
- %AU Margaret Recker
- %PU Proceedings of the Fifteenth Annual Meeting of the Cognitive Science
Society Conference, 1993
- %AV ftp://ftp.cc.gatech.edu/pub/ai/mimi/er-mr-93-03.ps.gz
- %OR GTECH
- %LT ER-MR-93/03
- %YR 1993
- %AB In earlier work, we presented results from an empirical study that
examined subjects' learning and browsing strategies as they explained
instructional materials to themselves that were contained in a
hypertext-based instructional environment. We developed a Soar model
that, through parameter manipulation, simulated the
strategies of each individual subject in the study. In this paper, we
explore the parameters of these simulations and
contribute several new
results. First, we show that a relatively small proportion of
strategies captured a large percentage of subjects' interaction
behaviors, suggesting that subjects' approach to the learning task
shared some underlying strategic commonalities. Second, we show that
lower performing subjects employed a high proportion of working memory
intensive strategies, which may have partially accounted for their
inferior performance. Third, clusters of subjects identified through
parameters analyses continued to exhibit similar behaviors during
subsequent problem solving, suggesting that the clusters corresponded
to genuine strategy classes. Furthermore, these clusters appeared to
represent general learning and browsing strategies that were, in some
sense, adaptive to the task.
- %TI A Methodology for Analyzing Students' Interactions within Educational
Hypertext
- %AU Margaret Recker
- %PU Educational Multimedia and Hypermedia Annual 1994
- %AV ftp://ftp.cc.gatech.edu/pub/ai/mimi/er-mr-94-01.ps.gz
- %OR GTECH
- %LT ER-MR-94/01
- %YR 1994
- %AB We present a theoretical approach and a methodology for
analyzing data from students interacting with and learning from
hypermedia systems. In our approach, interactions are viewed to be
mutually influenced by individual students' goals and strategies and
the actions supported by the interface of the learning environment.
The approach is illustrated by modelling data from an empirical study
in which students browsed through a hypertext instructional
environment to learn about programming concepts. By
using the explanatory power of the computational model, interactions
can be analyzed to determine patterns of use. Results obtained from
this method of analysis yield specific feedback on system design and
prescriptions for improving the design. More theoretically, they
provide valuable insights on the nature of human cognition and
learning in the context of interactive educational technologies.
- %TI Results for the first World Wide Web User Survey
- %AU James Pitkow and Mimi Recker
- %PU Journal of Computer Networks and ISDN Systems, Vol. 27, No. 2, 1994
- %PU Proceedings of the First World Wide Web Conference
- %AV ftp://ftp.cc.gatech.edu/pub/ai/mimi/er-mr-94-02.ps.gz
- %OR GTECH
- %LT ER-MR-94/02
- %YR 1994
- %AB The explosion of the World Wide Web (WWW) across the Internet is
staggering, both in terms of number of users and the amount of
activity. However, to date, no reliable characterizaition exists of
WWW users. In this paper, we report results from a survey that was
posted on the Web for a month, in January of 1994. There were
several goals motivating our survey. First, we wished to demonstrate
a proof of concept for WWW technologies as a useful survey medium.
Second, we wanted to beta-test the design and content of surveys
dealing with the Web. Third, as mentioned, we hoped to begin to
describe the range of Web users. In one month, we had over 4500
respondents to our survey. Their responses helped us to begin to
characterize WWW users, their reasons for using the WWW, and their
opinions of WWW tools and technologies.
- %TI Troubleshooting strategies in a complex, dynamical domain
- %AU M. Recker, T. Govindaraj, and V. Vasandani
- %PU Proceedings of the Annual Conference of the cognitive Science Society
- %AV ftp://ftp.cc.gatech.edu/pub/ai/mimi/er-mr-94-03.ps.gz
- %OR GTECH
- %LT ER-MR-94/03
- %YR 1994
- %AB In this paper, we present results from two empirical studies in which
subjects diagnosed faults that occurred in a computer-based, dynamical
simulation of an oil-fired marine power plant, called Turbinia. Our
results were analyzed in the framework of dual problem space
search (DPSS), in which non-routine diagnosis was characterized as a
process of generating hypotheses to explain the observed faults, and
testing these hypotheses by conducting experiments.
In the first study, we found that the less-efficient subjects
conducted significantly more experiments,
indicating a strong bottom-up bias in their diagnostic strategy. In the
second study, we examined the effects of imposing external resource
bounds on subjects' diagnostic strategies. Results indicated that
constraints on diagnosis time led to a reduction in the number of
actions performed and components viewed, without appearing to affect
diagnostic performance. Constraints on the number of diagnostic tests
reduced search in the experiment space, which appeared to negatively
affect performance. Taken together, these suggest results that
subjects' diagnostic strategies were sensitive to constraints in the
external task environment. We close with a sketch of how DPSS might
be augmented to include effects due to external resource bounds.
- %TI Cognitive Media Types as Indices for Hypermedia Learning Environments
- %AU M. Recker and A. Ram
- %PU 1994 AAAI Workshop on Indexing and Reuse in Multimedia Systems
- %AV ftp://ftp.cc.gatech.edu/pub/ai/mimi/er-mr-94-04.ps.gz
- %OR GTECH
- %LT ER-MR-94/04
- %YR 1994
- %AB In this paper, we propose a theoretical framework for designing indices for
educational hypermedia systems. In this theory, we argue that the
design of these systems and their and indices are best thought of
in terms of ``cognitive media types.'' Specifically, we argue that
systems should not be characterized primarily in terms of the kinds of
physical media types that can be accessed. Instead, the important
aspect is the content that can be represented within a physical media,
rather than the physical media itself. Cognitive media are based on a
cognitive theory of the inferential and learning processes of human
users, and encapsulate different methods or strategies for problem
solving and learning. These strategies rely on specific media
characteristics that facilitate specific problem solving actions,
which in turn are enabled by specific kinds of physical media.
- %TI Predicting Document Access in Large, Multimedia Repositories
- %AU M. Recker and J. Pitkow
- %PU Draft Paper
- %AV ftp://ftp.cc.gatech.edu/pub/ai/mimi/predict.ps.gz
- %OR GTECH
- %LT ER-MR-94/05
- %YR 1994
- %AB Network-accessible multimedia databases, repositories, and libraries
are proliferating at a rapid rate. A crucial problem for these
repositories remains timely and appropriate document access. In this
paper, we borrow a model from psychological research on human
memory, which has long studied retrieval of memory items based on
frequency and recency rates of past item occurrences. Specifically,
the model uses frequency and recency rates of prior document accesses
to predict future document requests. The model is illustrated by
analyzing the log file of document accesses to the Georgia Institute
of Technology World-Wide Web (WWW) database, a large multimedia
repository exhibiting high access rates. Results show that the model
predicts document access rates with a reliable degree of accuracy.
We describe extensions to the basic approach that combine
the recency and frequency analyses, and incorporate repository
structure and document type. These results have implications for the
formulation of descriptive user models of information access in large
repositories. In addition, we sketch applications in the areas of
design of information systems and interfaces, and their document
caching algorithms.
- %TI A Simple, Yet Robust Caching Algorithm Based on Dynamic Access Patterns
- %AU J. Pitkow and M. Recker
- %PU Proceedings of the Second World Wide Web Conference
- %AV ftp://ftp.cc.gatech.edu/pub/ai/mimi/caching.ps.gz
- %OR GTECH
- %LT ER-MR-94/06
- %YR 1994
- %AB The World-Wide Web continues its remarkable and seemingly
unregulated growth. This growth has seen a corresponding increase in
network loads and user response times. One common approach for
improving the retrieval rate of large, distributed documents is via
caching. In this paper, we present a caching algorithm that flexibly
adapt its parameters to the hit rates and access patterns of users
requesting documents. The algorithm is derived from an analysis of
user accesses in a WWW database. In particular, the analysis is based
upon a model from psychological research on human memory, which has
long studied retrieval of memory items based on frequency and recency
rates of past item occurrences. Results show that the model predicts
document access with a high degree of accuracy. Furthermore, the model
indicates that a caching algorithm based upon the recency rates of
prior document access will reliably handle future document
requests. The algorithm presented is simple, robust, and easily
implementable
- %TI Creative Conceptual Change
- %AU Ashwin Ram, Kenneth Moorman, Juan Carlos Santamaria
- %PU Technical Report GIT-CC-96/07, College of Computing, Georgia Institute of Technology, Atlanta, GA, 1996
- %PU A shorter version appears in the Fifteenth Annual Conference of the Cognitive Science Society, 17-26, Boulder, CO, June 1993
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-96-07.ps.Z
- %YR 1996
- %AB Creative conceptual change involves (a) the construction of new
concepts and of coherent belief systems, or theories, relating these
concepts, and (b) the modification and extrapolation of existing
concepts and theories in novel situations. We discuss these and
other types of conceptual change, and present computational models
of constructive and extrapolative processes in creative conceptual
change. The models have been implemented as computer programs in
two very different task domains, autonomous robotic navigation and
fictional story understanding.
- %TI Systematic Evaluation of Design Decisions in Case-Based Reasoning Systems
- %AU Juan Carlos Santamaria, Ashwin Ram
- %PU To appear in Case-Based Reasoning: Experiences, Lessons, and Future Directions, D.B. Leake, editor, AAAI Press
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/s-96-02.ps.Z
- %YR 1996
- %AB Two important goals in the evaluation of artificial intelligence systems
are to assess the merit of alternative design decisions in the
performance of an implemented computer system and to analyze the impact
in the performance when the system faces problem domains with different
characteristics. Achieving these objectives enables us to understand the
behavior of the system in terms of the theory and design of the
computational model, to select the best system configuration for a given
domain, and to predict how the system will behave when the
characteristics of the domain or problem change. In addition, for
case-based reasoning and other machine learning systems, it is important
to evaluate the improvement in the performance of the system with
experience (or with learning), to show that this improvement is
statistically significant, to show that the variability in performance
decreases with experience (convergence), and to analyze the impact of the
design decisions on this improvement in performance. We present a
methodology for the evaluation of CBR and other AI systems through
systematic empirical experimentation over a range of system
configurations and environmental conditions, coupled with rigorous
statistical analysis of the results of the experiments. We illustrate
this methodology with a case study in which we evaluate a multistrategy
case-based and reinforcement learning system which performs autonomous
robotic navigation. In this case study, we evaluate a range of design
decisions that are important in CBR systems, including configuration
parameters of the system (e.g., overall size of the case library, size or
extent of the individual cases), problem characteristics (e.g., problem
difficulty), knowledge representation decisions (e.g., choice of
representational primitives or vocabulary), algorithmic decisions (e.g.,
choice of adaptation method), and amount of prior experience (e.g.,
learning or training). We show how our methodology can be used to
evaluate the impact of these decisions on the performance of the system
and, in turn, to make the appropriate choices for a given problem domain
and verify that the system does behave as predicted.
- %TI Multi-Plan Retrieval and Adaptation in an Experience-Based Agent
- %AU Ashwin Ram, Anthony G. Francis, Jr.
- %PU To appear in Case-Based Reasoning: Experiences, Lessons, and Future Directions, D.B. Leake, editor, AAAI Press
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/s-96-01.ps.Z
- %YR 1996
- %AB The real world has many properties that present challenges for the design
of intelligent agents: it is dynamic, unpredictable, and independent,
poses poorly structured problems, and places bounds on the resources
available to agents. Agents that opearate in real worlds need a wide
range of capabilities to deal with them: memory, situation analysis,
situativity, resource-bounded cognition, and opportunism. We propose a
theory of experience-based agency which specifies how an agent with the
ability to richly represent and store its experiences could remember
those experiences with a context-sensitive, asynchronous memory,
incorporate those experiences into its reasoning on demand with
integration mechanisms, and usefully direct memory and reasoning through
the use of a utility-based metacontroller. We have implemented this
theory in an architecture called NICOLE and have used it to address the
problem of merging multiple plans during the course of case-based
adaptation in least-committment planning.
- %TI Evaluating Structural Organization of a Hypermedia Learning Environment using GOMS
- %AU Terry Shikano, Mimi Recker, Ashwin Ram
- %PU World Conference on Educational Multimedia and Hypermedia, Boston, MA, June 1996
- %AV mailto:ashwin@cc.gatech.edu
- %YR 1996
- %AB Network-accessibly hypermedia environments offer the potential for
radically changing the nature of education by providing students
with self-paced access to digital repositories of course
information. However, much research is still required to identify
ways to best organize, present, and index multimedia information for
maximizing use and learning by students. We have been developing a
theory of design for educational multimedia, which is based on
cognitive aspects of the users of that information. Design based on
"cognitive media types" appeals to the particular cognitive aspects
of learners. In contrast, design based on Òphysical media typesÓ
appeals to particular symbol systems or sensory modalities. To
evaluate our theory of cognitive media types, we have taken a
3-pronged approach: design, empirical evaluation, and analysis of
student models. In this paper, we focus on the third component of
our approach: a model of student usage and learning with cognitive
media. This model, based on the GOMS methodology, helps us better
understand the usability of our system, and how it may support and
hinder student learning. Furthermore, our user model provides
feedback on our theory of cognitive media, and offers suggestions
for the design of effective hypermedia learning environments.
- %TI Interacting Learning-Goals: Treating Learning as a Planning Task
- %AU Michael T. Cox, Ashwin Ram
- %PU In J.-P. Haton, M. Keane, & M. Manago (eds.), Topics in Case-Based Reasoning (Lecture Notes in Artificial Intelligence), 60-74, Springer-Verlag, 1995
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-95-09.ps.Z
- %YR 1995
- %AB This research examines the metaphor of goal-driven planning as a
tool for performing the integration of multiple learning
algorithms. In case-based reasoning systems, several learning
techniques may apply to a given situation. In a failure-driven
learning environment, the problems of strategy construction are to
choose and order the best set of learning algorithms or strategies
that recover from a processing failure and to use those strategies
to modify the system's background knowledge so that the failure will
not be repeated in similar future situations. A solution to this
problem is to treat learning-strategy construction as a planning
problem with its own set of goals. Learning goals, as opposed to
ordinary goals, specify desired states in the background knowledge
of the learner, rather than desired states in the external
environment of the planner. But as with traditional goal-based
planners, management and pursuit of these learning goals becomes a
central issue in learning. Example interactions of learning-goals
are presented from a multistrategy learning system called Meta-AQUA
that combines a case-based approach to learning with non linear
planning to achieve goals in a knowledge space.
- %TI Foundations of Foundations of Artificial Intelligence
- %AU Ashwin Ram, Eric Jones
- %PU Philosophical Psychology, 8(2):193-199, 1995
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-95-08.ps.Z
- %YR 1994
- %AB Review of D. Kirsh (ed.), Foundations of Artificial Intelligence,
MIT Press, 1992, containing papers by Kirsh, Nilsson, Birnbaum,
Hewitt, Gasser, Brooks, Lenat & Feigenbaum, Smith, Rosenbloom and
the Soar team, and Norman.
- %TI Cognitive Media Types for Multimedia Information Access
- %AU Mimi Recker, Ashwin Ram, Terry Shikano, George Li, John Stasko
- %PU Journal of Educational Multimedia and Hypermedia, 4(2/3):185, 1995.
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-95-07.ps.Z
- %YR 1995
- %AB Multimedia repositories, libraries, and databases offer the
potential for providing students with access to a wide variety of
interconnected information resources. However, in order to realize
this potential, multimedia systems should provide access to
information and activities that support effective knowledge
construction and learning by students. This article proposes a
theoretical framework for organizing information and activities in
educational hypermedia systems. We show that such systems should
not be characterized primarily in terms of the kinds of physical
media types that can be accessed; instead, the important aspect is
the content that can be represented within a physical media, rather
than the physical media itself. We propose a theory of ``cognitive
media types'' based on the inferential and learning processes of
human users. The theory highlights specific media characteristics
that facilitate specific problem solving actions, which in turn are
enabled by specific kinds of physical media. We present an
implemented computer system, called AlgoNet, that supports
hypermedia information access and constructive learning activities
for self-paced learning in computer and engineering disciplines.
Extensive empirical evaluations with undergraduate students suggest
that self-paced interactive learning environments, coupled with
multimedia information access and constructive activities organized
into cognitive media types, can support and help students develop
deep intuitions about important concepts in a given domain.
- %TI Structuring On-The-Job Troubleshooting Performance to Aid Learning
- %AU Brian Minsk, Harinarayanan Balakrishnan, Ashwin Ram
- %PU World Conference on Engineering Education, Minneapolis, MN, October 1995
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-95-06.ps.Z
- %YR 1995
- %AB This paper describes a methodology for aiding the learning of
troubleshooting tasks in the course of an engineer's work. The
approach supports learning in the context of actual, on-the-job
troubleshooting and, in addition, supports performance of the
troubleshooting task in tandem. This approach has been implemented
in a computer tool called WALTS (Workspace for Aiding and Learning
Troubleshooting). This method aids learning by helping the learner
structure his or her task into the conceptual components necessary
for troubleshooting, giving advice about how to proceed, suggesting
candidate hypotheses and solutions, and automatically retrieving
cognitively relevant media. WALTS includes three major components:
a structured dynamic workspace for representing knowledge about the
troubleshooting process and the device being diagnosed; an
intelligent agent that facilitates the troubleshooting process by
offering advice; and an intelligent media retrieval tool that
automatically presents candidate hypotheses and solutions, relevant
cases, and various other media. WALTS creates resources for future
learning and aiding of troubleshooting by storing completed
troubleshooting instances in a self-populating database of
troubleshooting cases. The methodology described in this paper is
partly based on research in problem-based learning, learning by
doing, case-based reasoning, intelligent tutoring systems, and the
transition from novice to expert. The tool is currently implemented
in the domain of remote computer troubleshooting.
- %TI Learning as Goal-Driven Inference
- %AU Ryszard Michalski, Ashwin Ram
- %PU In A. Ram & D. Leake (eds.), Goal-Driven Learning, chapter 21, MIT Press/Bradford Books, 1995
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-95-05.ps.Z
- %YR 1995
- %AB Developing an adequate and general computational model of adaptive,
multistrategy, and goal-oriented learning is a fundamental long-term
objective for machine learning research for both theoretical and
pragmatic reasons. We outline a proposal for developing such a
model based on two key ideas. First, we view learning as an active
process involving the formulation of learning goals during the
performance of a reasoning task, the prioritization of learning
goals, and the pursuit of learning goals using multiple learning
strategies. The second key idea is to model learning as a kind of
inference in which the system augments and reformulates its
knowledge using various types of primitive inferential actions,
known as knowledge transmutations.
- %TI Goal-Driven Learning in Multistrategy Reasoning and Learning Systems
- %AU Ashwin Ram, Michael T. Cox, S. Narayanan
- %PU In A. Ram & D. Leake (eds.), Goal-Driven Learning, chapter 18, MIT Press/Bradford Books, 1995
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-95-04.ps.Z
- %YR 1995
- %AB This chapter presents a computational model of introspective
multistrategy learning, which is a deliberative or strategic
learning process in which a reasoner introspects about its own
performance to decide what to learn and how to learn it. The
reasoner introspects about its own performance on a reasoning task,
assigns credit or blame for its performance, identifies what it
needs to learn to improve its performance, formulates learning goals
to acquire the required knowledge, and pursues its learning goals
using multiple learning strategies. Our theory models a process of
learning that is active, experiential, opportunistic, diverse, and
introspective. This chapter also describes two computer systems
that implement our theory, one that learns diagnostic knowledge
during a troubleshooting task and one that learns multiple kinds of
causal and explanatory knowledge during a story understanding task.
- %TI Goal-Driven Learning (Chapter 1: Learning, Goals, and Learning Goals)
- %AU Ashwin Ram, David Leake
- %PU MIT Press/Bradford Books, 1995
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-95-03.ps.Z
- %YR 1995
- %AB In cognitive science, artificial intelligence, psychology, and education,
a growing body of research supports the view that the learning process is
strongly influenced by the learner's goals. Investigators in each of
these areas have independently pursued the common issues of how learning
goals arise, how they affect learner decisions of when and what to learn,
and how they guide the learning process. The fundamental tenet of
goal-driven learning is that learning is largely an active and strategic
process in which the learner, human or machine, attempts to identify and
satisfy its information needs in the context of its tasks and goals, its
prior knowledge, its capabilities, and environmental opportunities for
learning. The book begins with a discussion of fundamental questions for
goal-driven learning: the motivations for adopting a goal-driven model of
learning, the basic goal-driven learning framework, the specific issues
raised by the framework that a theory of goal-driven learning must
address, the types of goals that can influence learning, the types of
influences those goals can have on learning, and the pragmatic
implications of the goal-driven learning model. The remaining chapters
address issues such as the justification of goal-driven learning models
through functional arguments about the role and utility of goals in
learning, the justification of such models through cognitive results,
goal-based processes for deciding what to learn and for guiding learning
and the learning process, and pragmatic implications of goal-driven
learning for design of instructional environments.
- %TI A Comparative Utility Analysis of Case-Based Reasoning and Control-Rule Learning Systems
- %AU Anthony Francis, Ashwin Ram
- %PU Eighth European Conference on Machine Learning (ECML-95), Crete, Greece, 1995
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-95-02.ps.Z
- %YR 1995
- %AB The utility problem in learning systems occurs when knowledge
learned in an attempt to improve a system's performance degrades
performance instead. We present a methodology for the analysis of
utility problems which uses computational models of problem solving
systems to isolate the root causes of a utility problem, to detect
the threshold conditions under which the problem will arise, and to
design strategies to eliminate it. We present models of case-based
reasoning and control-rule learning systems and compare their
performance with respect to the swamping utility problem. Our
analysis suggests that case-based reasoning systems are more
resistant to the utility problem than control-rule learning systems.
- %TI Multimedia Information Access in Support of Knowledge Construction
- %AU Mimi Recker, Ashwin Ram, George Li, Terry Shikano, John Stasko
- %PU Annual Meeting of the American Educational Research Association, San Franciso, 1995 (extended abstract)
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-95-01.txt.Z
- %YR 1995
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/er-95-07.ps.Z
- %TI Understanding the Creative Mind
- %AU Ashwin Ram, Linda Wills, Eric Domeshek, Nancy Nersessian, Janet Kolodner
- %PU Artificial Intelligence journal, 79(1):111-128, 1995
- %PU Technical Report GIT-CC-94/13, College of Computing, Georgia Institute of Technology, Atlanta, GA, 1994
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-94-13.ps.Z
- %YR 1994
- %AB A review of Margaret Boden's "The Creative Mind", discussing
creativity and computational models of creativity.
- %TI Managing Learning Goals in Strategy Selection Problems
- %AU Michael T. Cox, Ashwin Ram
- %PU Second European Workshop on Case-Based Reasoning, Chantilly, France, 1994
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-94-11.ps.Z
- %YR 1994
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/s-95-01.ps.Z
- %TI Integrating Creativity and Reading: A Functional Approach
- %AU Kenneth Moorman, Ashwin Ram
- %PU Sixteenth Annual Conference of the Cognitive Science Society, Atlanta, GA, August 1994
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-94-10.ps.Z
- %YR 1994
- %AB Reading has been studied for decades by a variety of cognitive
disciplines, yet no theories exist which sufficiently describe and
explain how people accomplish the complete task of reading
real-world texts. In particular, a type of knowledge intensive
reading known as creative reading has been largely ignored by the
past research. We argue that creative reading is an aspect of
practically all reading experiences; as a result, any theory which
overlooks this will be insufficient. We have built on results from
psychology, artificial intelligence, and education in order to
produce a functional theory of the complete reading process. The
overall framework describes the set of tasks necessary for reading
to be performed. Within this framework, we have developed a theory
of creative reading. The theory is implemented in the ISAAC
(Integrated Story Analysis And Creativity) system, a reading system
which reads science fiction stories.
- %TI Failure-Driven Learning as Input Bias
- %AU Michael T. Cox, Ashwin Ram
- %PU Sixteenth Annual Conference of the Cognitive Science Society, Atlanta, GA, August 1994
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-94-09.ps.Z
- %YR 1994
- %AB Self-selection of input examples on the basis of performance failure
is a powerful bias for learning systems. The definition of what
constitutes a learning bias, however, has been typically restricted
to bias provided by the input language, hypothesis language, and
preference criteria between competing concept hypotheses. But if
bias is taken in the broader context as any basis that provides a
preference for one concept change over another, then the paradigm of
failure-driven processing indeed provides a bias. Bias is exhibited
by the selection of examples from an input stream that are examples
of failure; successful performance is filtered out. We show that
the degrees of freedom are less in failure-driven learning than in
success-driven learning and that learning is facilitated because of
this constraint. We also broaden the definition of failure, provide
a novel taxonomy of failure causes, and illustrate the interaction
of both in a multistrategy learning system called Meta-AQUA.
- %TI Cognitive Media Types as Indices for Hypermedia Learning Environments
- %AU Mimi Recker, Ashwin Ram
- %PU AAAI Workshop on Indexing and Reuse in Multimedia Systems, Seattle, WA, August 1994
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-94-07.ps.Z
- %YR 1994
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/er-95-07.ps.Z
- %TI A Comparative Utility Analysis of Case-Based Reasoning and Control-Rule Learning Systems
- %AU Anthony Francis, Ashwin Ram
- %PU AAAI Workshop on Case-Based Reasoning, Seattle, WA, August 1994
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-94-06.ps.Z
- %YR 1994
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/er-95-02.ps.Z
- %TI Systematic Evaluation of Design Decisions in Case-Based Reasoning Systems
- %AU Juan Carlos Santamaria, Ashwin Ram
- %PU AAAI Workshop on Case-Based Reasoning, Seattle, WA, August 1994
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-94-05.ps.Z
- %YR 1994
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/s-96-02.ps.Z
- %TI A Model of Creative Understanding
- %AU Kenneth Moorman, Ashwin Ram
- %PU Twelvth National Conference on Artificial Intelligence (AAAI-94), Seattle, WA, August 1994
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-94-04.ps.Z
- %YR 1994
- %AB Although creativity has largely been studied in problem solving
contexts, creativity consists of both a generative component and a
comprehension component. In particular, creativity is an essential
part of reading and understanding of natural language stories. We
have formalized the understanding process and have developed an
algorithm capable of producing creative understanding behavior. We
have also created a novel knowledge organization scheme to assist
the process. Our model of creativity is implemented as a portion of
the ISAAC (Integrated Story Analysis And Creativity) reading system,
a system which models the creative reading of science fiction
stories.
- %TI Choosing Learning Strategies to Achieve Learning Goals
- %AU Michael T. Cox, Ashwin Ram
- %PU AAAI Spring Symposium on Goal-Driven Learning, 12-21, Stanford, CA, 1994
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-94-03.ps.Z
- %YR 1994
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/s-95-01.ps.Z
- %TI A Framework for Goal-Driven Learning
- %AU Ashwin Ram, David Leake
- %PU AAAI Spring Symposium on Goal-Driven Learning, Stanford, CA, 1994
- %PU Full version in A. Ram & D. Leake, editors, Goal-Driven Learning,
MIT Press/Bradford Books, 1995
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-94-02.ps.Z
- %YR 1994
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/er-95-03.ps.Z
- %TI Using Genetic Algorithms to Learn Reactive Control Parameters for Autonomous Robotic Navigation
- %AU Ashwin Ram, Ronald Arkin, Gary Boone, Michael Pearce
- %PU Adaptive Behavior, 2(3):277-305, 1994
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-94-01.ps.Z
- %YR 1994
- %AB This paper explores the application of genetic algorithms to the
learning of local robot navigation behaviors for reactive control
systems. Our approach evolves reactive control systems in various
environments, thus creating sets of ``ecological niches'' that can
be used in similar environments. The use of genetic algorithms as an
unsupervised learning method for a reactive control architecture
greatly reduces the effort required to configure a navigation
system. Unlike standard genetic algorithms, our method uses a
floating point gene representation. The system is fully implemented
and has been evaluated through extensive computer simulations of
robot navigation through various types of environments.
- %TI A Functional Theory of Creative Reading
- %AU Kenneth Moorman, Ashwin Ram
- %PU The Psycgrad Journal
- %PU Technical Report GIT-CC-94/01, College of Computing, Georgia Institute of Technology, Atlanta, GA, 1994
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-94-01.ps.Z
- %YR 1994
- %AB Reading is an area of human cognition which has been studied for
decades by psychologists, education researchers, and artificial
intelligence researchers. Yet, there still does not exist a theory
which accurately describes the complete process. We believe that
these past attempts fell short due to an incomplete understanding of
the overall task of reading; namely, the complete set of mental
tasks a reasoner must perform to read and the mechanisms that carry
out these tasks. We present a functional theory of the reading
process and argue that it represents a coverage of the task. The
theory combines experimental results from psychology, artificial
intelligence, education, and linguistics, along with the insights we
have gained from our own research. This greater understanding of
the mental tasks necessary for reading will enable new natural
language understanding systems to be more flexible and more capable
than earlier ones. Furthermore, we argue that creativity is a
necessary component of the reading process and must be considered in
any theory or system attempting to describe it. We present a
functional theory of creative reading and a novel knowledge
organization scheme that supports the creativity mechanisms. The
reading theory is currently being implemented in the ISAAC
(Integrated Story Analysis And Creativity) system, a computer system
which reads science fiction stories.
- %TI Learning to Troubleshoot: Multistrategy Learning of Diagnostic Knowledge for a Real-World Problem Solving Task
- %AU Ashwin Ram, S. Narayanan, Michael T. Cox
- %PU Cognitive Science journal, 19(3):289-340, 1995
- %PU Technical Report GIT-CC-93/67, College of Computing, Georgia Institute of Technology, Atlanta, GA, 1993
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-93-67.ps.Z
- %YR 1993
- %AB This article presents a computational model of the learning of
diagnostic knowledge based on observations of human operators
engaged in a real-world troubleshooting task. We present a model of
problem solving and learning in which the reasoner introspects about
its own performance on the problem solving task, identifies what it
needs to learn to improve its performance, formulates learning goals
to acquire the required knowledge, and pursues its learning goals
using multiple learning strategies. The model is implemented in a
computer system which provides a case study based on observations of
troubleshooting operators and protocol analysis of the data gathered
in the test area of an operational electronics manufacturing plant.
The model is intended as a computational model of human learning; in
addition, it is computationally justified as a uniform, extensible
framework for multistrategy learning.
- %TI Multistrategy Learning in Reactive Control Systems for Autonomous Robotic Navigation
- %AU Ashwin Ram, Juan Carlos Santamaria
- %PU Informatica, 17(4):347-369, 1993
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-93-09.ps.Z
- %YR 1993
- %AB This paper presents a self-improving reactive control system for
autonomous robotic navigation. The navigation module uses a
schema-based reactive control system to perform the navigation task.
The learning module combines case-based reasoning and reinforcement
learning to continuously tune the navigation system through
experience. The case-based reasoning component perceives and
characterizes the system's environment, retrieves an appropriate
case, and uses the recommendations of the case to tune the
parameters of the reactive control system. The reinforcement
learning component refines the content of the cases based on the
current experience. Together, the learning components perform
on-line adaptation, resulting in improved performance as the
reactive control system tunes itself to the environment, as well as
on-line case learning, resulting in an improved library of cases
that capture environmental regularities necessary to perform on-line
adaptation. The system is extensively evaluated through simulation
studies using several performance metrics and system configurations.
- %TI AQUA: Questions that Drive the Explanation Process
- %AU Ashwin Ram
- %PU Inside Case-Based Explanation, R.C. Schank, A. Kass, and C.K. Riesbeck (eds.), 207-261, Lawrence Erlbaum, 1994
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-93-47.ps.Z
- %YR 1993
- %AB In the doctoral disseration from which this chapter is drawn, Ashwin Ram
presented an alternative perspective on the processes of story
understanding, explanation, and learning. The issues that Ram explores
in that dissertation are similar to those that are explored by the other
authors in this book, but the angle that Ram takes on these issues is
somewhat different. Ram's exploration of these processes is organized
around the central theme of question asking. For Ram, understanding a
story means identifying questions that the story raises, and questions
that it answers. Question asking also serves as a lens through which
each of the sub-processes of is viewed: the retrieval of stored
explanations, for instance, is driven by a library of what Ram calls "XP
retrieval questions"; likewise, evaluation is driven by another set of
questions, called "hypothesis verification questions". The AQUA program,
which is Ram's implementation of this question-based theory of
understanding, is a very complex system, probably the most complex among
the programs described in this book. AQUA covers a great deal of ground;
it implements the entire case-based explanation process in a
question-based manner. In this chapter, we have focussed on the
high-level description of the questions the programs asks, especially the
questions it asks when constructing and evaluating explanations of
volitional actions.
- %TI The Utility Problem in Case-Based Reasoning
- %AU Anthony G. Francis, Jr., Ashwin Ram
- %PU Abstracted in the AAAI-93 Workshop on Case-Based Reasoning, Washington, DC, July 1993
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-93-08.ps.Z
- %YR 1993
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/er-95-02.ps.Z
- %TI Knowledge Compilation and Speedup Learning in Continuous Task Domains
- %AU Juan Carlos Santamaria, Ashwin Ram
- %PU ML-93 Workshop on Knowledge Compilation and Speedup Learning, Amherst, MA, June 1993
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-93-07.ps.Z
- %YR 1993
- %AB Many techniques for speedup learning and knowledge compilation focus
on the learning and optimization of macro-operators or control rules
in task domains that can be characterized using a problem-space
search paradigm. However, such a characterization does not fit well
the class of task domains in which the problem solver is required to
perform in a continuous manner. For example, in many robotic
domains, the problem solver is required to monitor real-valued
perceptual inputs and vary its motor control parameters in a
continuous, on-line manner to successfully accomplish its task. In
such domains, discrete symbolic states and operators are difficult
to define. To improve its performance in continuous problem
domains, a problem solver must learn, modify, and use "continuous
operators" that continuously map input sensory information to
appropriate control outputs. Additionally, the problem solver must
learn the contexts in which those continuous operators are
applicable. We propose a learning method that can compile
sensorimotor experiences into continuous operators, which can then
be used to improve performance of the problem solver. The method
speeds up the task performance as well as results in improvements in
the quality of the resulting solutions. The method is implemented
in a robotic navigation system, which is evaluated through extensive
experimentation.
- %TI Computational Models of the Utility Problem and their Application to Utility Analysis of Case-Based Reasoning
- %AU Anthony G. Francis, Jr., Ashwin Ram
- %PU ML-93 Workshop on Knowledge Compilation and Speedup Learning, Amherst, MA, June 1993
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-93-06.ps.Z
- %YR 1993
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/er-95-02.ps.Z
- %TI Continuous Case-Based Reasoning
- %AU Ashwin Ram, Juan Carlos Santamaria
- %PU AAAI Workshop on Case-Based Reasoning, 86-93, Washington DC, July 1993
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-93-05.ps.Z
- %YR 1993
- %AB Case-based reasoning systems have traditionally been used to perform
high-level reasoning in problem domains that can be adequately
described using discrete, symbolic representations. However, many
real-world problem domains, such as autonomous robotic navigation,
are better characterized using continuous representations. Such
problem domains also require continuous performance, such as
continuous sensorimotor interaction with the environment, and
continuous adaptation and learning during the performance task. We
introduce a new method for "continuous case-based reasoning," and
discuss how it can be applied to the dynamic selection,
modification, and acquisition of robot behaviors in autonomous
navigation systems. We conclude with a general discussion of
case-based reasoning issues addressed by this work.
- %TI Creative Conceptual Change
- %AU Ashwin Ram
- %PU Fifteenth Annual Conference of the Cognitive Science Society, 17-26, Boulder, CO, June 1993
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-93-04.ps.Z
- %YR 1993
- %AB Superceded by ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-96-07.ps.Z
- %TI A Multistrategy Case-Based and Reinforcement Learning Approach to Self-Improving Reactive Control Systems for Autonomous Robotic Navigation
- %AU Ashwin Ram, Juan Carlos Santamaria
- %PU Second International Workshop on Multistrategy Learning, Harpers Ferry, WV, May 1993
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-93-03.ps.Z
- %YR 1993
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/er-93-09.ps.Z
- %TI A New Perspective on Story Understanding
- %AU Kenneth Moorman, Ashwin Ram
- %PU Thirty-First Southeast ACM Conference, Birmingham, AL, April 1993
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-93-02.ps.Z
- %YR 1993
- %AU Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/er-94-10.ps.Z
- %TI Goal-Driven Learning: Fundamental Issues and Symposium Report
- %AU David Leake, Ashwin Ram
- %PU AI Magazine, 14(4):67-72, Winter 1993
- %PU Technical Report #85, Cognitive Science Program, Indiana University, Bloomington, IN, 1993
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-93-01.ps.Z
- %YR 1993
- %AB In Artificial Intelligence, Psychology, and Education, a growing
body of research supports the view that learning is a goal-directed
process. Psychological experiments show that people with different
goals process information differently; studies in education show
that goals have strong effects on what students learn; and
functional arguments from machine learning support the necessity of
goal-based focusing of learner effort. At the Fourteenth Annual
Conference of the Cognitive Science Society, a symposium brought
together researchers in AI, psychology, and education to discuss
goal-driven learning. This article presents the fundamental points
illuminated by the symposium, placing them in the context of open
questions and current research directions in goal-driven learning.
- %TI Case-Based Reactive Navigation: A Case-Based Method for On-Line Selection and Adaptation of Reactive Control Parameters in Autonomous Robotic Systems
- %AU Ashwin Ram, Ronald C. Arkin, Kenneth Moorman, Russell J. Clark
- %PU To appear in IEEE Transactions on Systems, Man, and Cybernetics
- %PU Technical Report GIT-CC-92/57, College of Computing, Georgia Institute of Technology, Atlanta, GA, 1992
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-92-57.ps.Z
- %YR 1992
- %AB This article presents a new line of research investigating on-line
learning mechanisms for autonomous intelligent agents. We discuss a
case-based method for dynamic selection and modification of behavior
assemblages for a navigational system. The case-based reasoning
module is designed as an addition to a traditional reactive control
system, and provides more flexible performance in novel environments
without extensive high-level reasoning that would otherwise slow the
system down. The method is implemented in the ACBARR (A Case-BAsed
Reactive Robotic) system, and evaluated through empirical simulation
of the system on several different environments, including "box
canyon" environments known to be problematic for reactive control
systems in general.
- %TI Introspective Reasoning using Meta-Explanations for Multistrategy Learning
- %AU Ashwin Ram, Michael T. Cox
- %PU Machine Learning: A Multistrategy Approach, Vol. IV, R.S. Michalski and G. Tecuci (eds.), 349-377, Morgan Kaufmann, 1994
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-92-19.ps.Z
- %YR 1992
- %AB In order to learn effectively, a reasoner must not only possess
knowledge about the world and be able to improve that knowledge, but
it also must introspectively reason about how it performs a given
task and what particular pieces of knowledge it needs to improve its
performance at the current task. Introspection requires declarative
representations of meta-knowledge of the reasoning performed by the
system during the performance task, of the system's knowledge, and
of the organization of this knowledge. This paper presents a
taxonomy of possible reasoning failures that can occur during a
performance task, declarative representations of these failures, and
associations between failures and particular learning strategies.
The theory is based on Meta-XPs, which are explanation structures
that help the system identify failure types, formulate learning
goals, and choose appropriate learning strategies in order to avoid
similar mistakes in the future. The theory is implemented in a
computer model of an introspective reasoner that performs
multistrategy learning during a story understanding task.
- %TI The Use of Explicit Goals for Knowledge to Guide Inference and Learning
- %AU Ashwin Ram, Lawrence Hunter
- %PU Journal of Applied Intelligence, 2(1):47-73, 1992
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-92-04.ps.Z
- %YR 1992
- %AB Combinatorial explosion of inferences has always been a central
problem in artificial intelligence. Although the inferences that
can be drawn from a reasoner's knowledge and from available inputs
is very large (potentially infinite), the inferential resources
available to any reasoning system are limited. With limited
inferential capacity and very many potential inferences, reasoners
must somehow control the process of inference. Not all inferences
are equally useful to a given reasoning system. Any reasoning
system that has goals (or any form of a utility function) and acts
based on its beliefs indirectly assigns utility to its beliefs.
Given limits on the process of inference, and variation in the
utility of inferences, it is clear that a reasoner ought to draw the
inferences that will be most valuable to it. This paper presents an
approach to this problem that makes the utility of a (potential)
belief an explicit part of the inference process. The method is to
generate explicit desires for knowledge. The question of focus of
attention is thereby transformed into two related problems: How can
explicit desires for knowledge be used to control inference and
facilitate resource-constrained goal pursuit in general? and, Where
do these desires for knowledge come from? We present a theory of
knowledge goals, or desires for knowledge, and their use in the
processes of understanding and learning. The theory is illustrated
using two case studies, a natural language understanding program
that learns by reading novel or unusual newspaper stories, and a
differential diagnosis program that improves its accuracy with
experience.
- %TI Indexing, Elaboration and Refinement: Incremental Learning of Explanatory Cases
- %AU Ashwin Ram
- %PU Machine Learning, 10:201-248, 1993.
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-92-03.ps.Z
- %YR 1992
- %AB This article describes how a reasoner can improve its understanding
of an incompletely understood domain through the application of what
it already knows to novel problems in that domain. Case-based
reasoning is the process of using past experiences stored in the
reasoner's memory to understand novel situations or solve novel
problems. However, this process assumes that past experiences are
well understood and provide good "lessons" to be used for future
situations. This assumption is usually false when one is learning
about a novel domain, since situations encountered previously in
this domain might not have been understood completely. Furthermore,
the reasoner may not even have a case that adequately deals with the
new situation, or may not be able to access the case using existing
indices. We present a theory of incremental learning based on the
revision of previously existing case knowledge in response to
experiences in such situations. The theory has been implemented in
a case-based story understanding program that can (a) learn a new
case in situations where no case already exists, (b) learn how to
index the case in memory, and (c) incrementally refine its
understanding of the case by using it to reason about new
situations, thus evolving a better understanding of its domain
through experience. This research complements work in case-based
reasoning by providing mechanisms by which a case library can be
automatically built for use by a case-based reasoning program.
- %TI A Theory of Questions and Question Asking
- %AU Ashwin Ram
- %PU The Journal of the Learning Sciences, 1(3&4):273-318, 1991
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-92-02.ps.Z
- %YR 1992
- %AB This article focusses on knowledge goals, that is, the goals of a
reasoner to acquire or reorganize knowledge. Knowledge goals, often
expressed as questions, arise when the reasoner's model of the
domain is inadequate in some reasoning situation. This leads the
reasoner to focus on the knowledge it needs, to formulate questions
to acquire this knowledge, and to learn by pursuing its questions.
I develop a theory of questions and of question-asking, motivated
both by cognitive and computational considerations, and I discuss
the theory in the context of the task of story understanding. I
present a computer model of an active reader that learns about novel
domains by reading newspaper stories.
- %TI A Case-Based Approach to Reactive Control for Autonomous Robots
- %AU Kenneth Moorman, Ashwin Ram
- %PU AAAI Fall Symposium on AI for Real-World Autonomous Robots, Cambridge, MA, October 1992
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-92-07.ps.Z
- %YR 1992
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-92-57.ps.Z
- %TI An Explicit Representation of Forgetting
- %AU Michael T. Cox, Ashwin Ram
- %PU Sixth International Conference on Systems Research, Informatics and Cybernetics, Baden-Baden, Germany, August, 1992
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-92-06.ps.Z
- %YR 1992
- %AB A pervasive, yet much ignored, factor in the analysis of processing
failures is the problem of misorganized knowledge. If a system's
knowledge is not indexed or organized correctly, it may make an
error, not because it does not have either the general capability or
specific knowledge to solve a problem, but rather because it does
not have the knowledge sufficiently organized so that the
appropriate knowledge structures are brought to bear on the problem
at the appropriate time. In such cases, the system can be said to
have "forgotten" the knowledge, if only in this context. This is
the problem of forgetting or retrieval failure. This research
presents an analysis along with a declarative representation of a
number of types of forgetting errors. Such representations can
extend the capability of introspective failure-driven learning
systems, allowing them to reduce the likelihood of repeating such
errors. Examples are presented from the Meta-AQUA program, which
learns to improve its performance on a story understanding task
through an introspective meta-analysis of its knowledge, its
organization of its knowledge, and its reasoning processes.
- %TI Learning to Troubleshoot in Electronics Assembly Manufacturing
- %AU S. Narayanan, Ashwin Ram
- %PU Machine learning: Ninth International Conference, Workshop on Integrated Learning in Real-world Domains, Aberdeen, Scotland, July 1992
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-92-05.ps.Z
- %YR 1992
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-93-67.ps.Z
- %TI An Architecture for Integrated Introspective Learning
- %AU Ashwin Ram, Michael T. Cox, S. Narayanan
- %PU Machine Learning: Ninth International Conference, Workshop on Computational Architectures, Aberdeen, Scotland, July 1992
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-92-04.ps.Z
- %YR 1992
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/er-95-04.ps.Z
- %TI Multistrategy Learning with Introspective Meta-Explanations
- %AU Michael T. Cox
- %AU Ashwin Ram
- %PU Machine Learning: Ninth International Conference, Aberdeen, Scotland, July 1992
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-92-03.ps.Z
- %YR 1992
- %AB Given an arbitrary learning situation, it is difficult to determine
the most appropriate learning strategy. The goal of this research is
to provide a general representation and processing framework for
introspective reasoning for strategy selection. The learning
framework for an introspective system is to first perform some
reasoning task. As it does, the system also records a trace of the
reasoning itself, along with the results of such reasoning. If a
reasoning failure occurs, the system must retrieve and apply an
introspective explanation of the failure in order to understand the
error and repair the knowledge base. A knowledge structure called a
Meta-Explanation Pattern is used to both explain how conclusions are
derived and why such conclusions fail. If reasoning is represented
in an explicit, declarative manner, the system can examine its own
reasoning, analyze its reasoning failures, identify what it needs to
learn, and select appropriate learning strategies in order to learn
the required knowledge without overreliance on the programmer.
- %TI The Learning of Reactive Control Parameters through Genetic Algorithms
- %AU Michael Pearce, Ronald C. Arkin, Ashwin Ram
- %PU IEEE/RSJ International Conference on Intelligent Robots and Systems, 130-137, Raleigh, NC, 1992
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-92-02.ps.Z
- %YR 1992
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/er-94-01.ps.Z
- %TI Knowledge-Based Diagnostic Problem Solving and Learning in the Test Area of Electronics Assembly Manufacturing
- %AU S. Narayanan, Ashwin Ram, Sally M. Cohen, Christine M. Mitchell, T. Govindraj
- %PU SPIE Symposium on Applications of AI X: Knowledge-Based Systems, Orlando, FL, April 1992
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-92-01.ps.Z
- %YR 1992
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-93-67.ps.Z
- %TI Learning Momentum: On-line Performance Enhancement for Reactive Systems
- %AU Russell J. Clark, Ronald C. Arkin, Ashwin Ram
- %PU IEEE International Conference on Robotics and Automation, 111-116, Nice, France, May 1992
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-91-37.ps.Z
- %YR 1991
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-92-57.ps.Z
- %TI Interest-based Information Filtering and Extraction in Natural Language Understanding Systems
- %AU Ashwin Ram
- %PU Bellcore Workshop on High-Performance Information Filtering, Morristown, NJ, November 1991
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-91-05.ps.Z
- %YR 1991
- %AB Given the vast amount of information available to the average
person, there is a growing need for mechanisms that can select
relevant or useful information based on some specification of the
interests of a user. Furthermore, experience with natural language
understanding and reasoning programs in artificial intelligence has
demonstrated that the combinatorial explosion of possible
conclusions that can be drawn from any input is a serious
computational bottleneck in the design of computer programs that
process information automatically. This paper presents a theory of
interestingness that serves as the basis for two story understanding
programs, one that can filter and extract information likely to be
relevant or interesting to a user, and another that can formulate
and pursue its own interests based on an analysis of the information
necessary to carry out the tasks it is pursuing. We discuss the
basis for our theory of interestingness, heuristics for
interest-based processing of information, and the process used to
filter and extract relevant information from the input.
- %TI Using Introspective Reasoning to Select Learning Strategies
- %AU Michael Cox, Ashwin Ram
- %PU First International Workshop on Multistrategy Learning, 217-230, Harpers Ferry, WV, November 1991
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-91-04.ps.Z
- %YR 1991
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-92-19.ps.Z
- %TI Evaluation of Explanatory Hypotheses
- %AU Ashwin Ram, David Leake
- %PU Thirteenth Annual Conference of the Cognitive Science Society, 867-871, Chicago, IL, August 1991
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-91-03.ps.Z
- %YR 1991
- %AB Abduction is often viewed as inference to the "best" explanation.
However, the evaluation of the goodness of candidate hypotheses
remains an open problem. Most artificial intelligence research
addressing this problem has concentrated on syntactic criteria,
applied uniformly regardless of the explainer's intended use for the
explanation. We demonstrate that syntactic approaches are
insufficient to capture important differences in explanations, and
propose instead that choice of the "best" explanation should be
based on explanations' utility for the explainer's purpose. We
describe two classes of goals motivating explanation: knowledge
goals reflecting internal desires for information, and goals to
accomplish tasks in the external world. We describe how these goals
impose requirements on explanations, and discuss how we apply those
requirements to evaluate hypotheses in two computer story
understanding systems.
- %TI A Goal-based Approach to Intelligent Information Retrieval
- %AU Ashwin Ram, Lawrence Hunter
- %PU Machine Learning: Eighth International Workshop, Chicago, IL, June 1991
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-91-02.ps.Z
- %YR 1991
- %AB Intelligent information retrieval (IIR) requires inference. The
number of inferences that can be drawn by even a simple reasoner is
very large, and the inferential resources available to any practical
computer system are limited. This problem is one long faced by AI
researchers. In this paper, we present a method used by two recent
machine learning programs for control of inference that is relevant
to the design of IIR systems. The key feature of the approach is
the use of explicit representations of desired knowledge, which we
call knowledge goals. Our theory addresses the representation of
knowledge goals, methods for generating and transforming these
goals, and heuristics for selecting among potential inferences in
order to feasibly satisfy such goals. In this view, IIR becomes a
kind of planning: decisions about what to infer, how to infer and
when to infer are based on representations of desired knowledge, as
well as internal representations of the system's inferential
abilities and current state. The theory is illustrated using two
case studies, a natural language understanding program that learns
by reading novel newspaper stories, and a differential diagnosis
program that improves its accuracy with experience. We conclude by
making several suggestions on how this machine learning framework
can be integrated with existing information retrieval methods.
- %TI Learning Indices for Schema Selection
- %AU Sambasiva Bhatta, Ashwin Ram
- %PU Florida Artificial Intelligence Research Symposium, 226-231, Cocoa Beach, FL, April 1991
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-91-01.ps.Z
- %YR 1991
- %AB In addition to learning new knowledge, a system must be able to
learn when the knowledge is likely to be applicable. An index is a
piece of information which, when identified in a given situation,
triggers the relevant piece of knowledge (or schema) in the system's
memory. We discuss the issue of how indices may be learned
automatically in the context of a story understanding task, and
present a program that can learn new indices for existing
explanatory schemas. We discuss two methods using which the system
can identify the relevant schema even if the input does not directly
match an existing index, and learn a new index to allow it to
retrieve this schema more efficiently in the future.
- %TI Decision Models: A Theory of Volitional Explanation
- %AU Ashwin Ram
- %PU Twelvth Annual Conference of the Cognitive Science Society, Cambridge, MA, July 1990
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-90-03.ps.Z
- %YR 1990
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-93-47.ps.Z
- %TI Knowledge Goals: A Theory of Interestingness
- %AU Ashwin Ram
- %PU Twelvth Annual Conference of the Cognitive Science Society, 206-214, Cambridge, MA, July 1990
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-90-02.ps.Z
- %YR 1990
- %AB Combinatorial explosion of inferences has always been one of the
classic problems in AI. Resources are limited, and inferences
potentially infinite; a reasoner needs to be able to determine which
inferences are useful to draw from a given piece of text. But
unless one considers the goals of the reasoner, it is very difficult
to give a principled definition of what it means for an inference to
be "useful." This paper presents a theory of inference control
based on the notion of interestingness. We introduce knowledge
goals, the goals of a reasoner to acquire some piece of knowledge
required for a reasoning task, as the focussing criteria for
inference control. We argue that knowledge goals correspond to the
interests of the reasoner, and present a theory of interestingness
that is functionally motivated by consideration of the needs of the
reasoner. Although we use story understanding as the reasoning
task, many of the arguments carry over to other cognitive tasks as
well.
- %TI Incremental Learning of Explanation Patterns and their Indices
- %AU Ashwin Ram
- %PU Seventh International Conference on Machine Learning, 313-320, Austin, TX, June 1990
- %AV ftp://ftp.cc.gatech.edu/pub/ai/ram/er-90-01.ps.Z
- %YR 1990
- %AB Subsumed by ftp://ftp.cc.gatech.edu/pub/ai/ram/git-cc-92-03.ps.Z
- %TI A Computational Theory of Children's Learning About Number
Conservation
- %AU Tony J. Simon & David Klahr
- %PU In T.J. Simon & G.S. Halford (Eds.) Developing Cognitive
Competence: New Approaches to Process Modeling. LEA. (in press)
- %AV ftp://ftp.cc.gatech.edu/pub/ai/simon/Q-Soar.tech.rtf
- %OR GTECH & CMU
- %LT GIT-CS-94/11
- %YR 1994
- %AB This chapter presents a model of the construction of number
conservation knowledge by preschool children. The model, Q-Soar,
simulates a published training study where 3- and 4 year-old children
who initially failed conservation problems were trained to
successfully make conservation judgments. The central point of Q-Soar
is that arrays of objects are quantified before and after a
transformation is observed and the resulting representations are
compared. The quantitative outcome is then attributed to the
transformation as its effect. Sub-problems of the whole task create
what are known as impasses and these determine the learning that
Soar's learning mechanism, called chunking, carries out. The result of
the processing executed as a function of the impasses creates new and
more general knowledge that Q-Soar can later use to simply recognize,
rather than compute, the conserving or non-conserving effects of
familiar transformations. The model learns from the same trials as the
children in the published study. It also embodies an account of the
differences between the younger and older subjects in terms of the
knowledge and processes that are being used by the two age groups to
solve the problems they are presented with.
- %TI Do Infants Understand Simple Arithmetic or Only Physics?
- %AU Tony J. Simon, Susan J. Hespos & Philippe Rochat
- %PU Technical Report GIT-CS-94/09, Cognitive Science Program, College of
Computing, Georgia Institute of Technology, Atlanta, GA, 1994
- %AV ftp://ftp.cc.gatech.edu/pub/ai/simon/Infant.tech.rtf
- %OR GTECH & EMORY
- %LT GIT-CS-94/09
- %YR 1994
- %AB Numerical competence in 5-month-old infants is investigated using a
violation-of-expectation paradigm. An experiment is reported which
replicates the findings of Wynn (1992). In additional conditions,
5-month-olds are shown to be sensitive to impossible outcomes
following addition or subtraction operations on small sets of objects,
regardless of identity changes. Wynn's interpretation of innate
arithmetical ability is discussed in detail and put into question. An
alternative explanation of infants' behavior in this task is proposed.
Rather than a manifestation of arithmetical competence, we propose
that infants' responses are based on their knowledge of the principles
of physical object behavior as described by Baillargeon, Spelke and
others. (Revised version In Press Cognitive Development Journal 1995).
- %TI Computational Models and Cognitive Change
- %AU Tony J. Simon & Graeme S. Halford
- %PU In T.J. Simon & G.S. Halford (Eds.) Developing Cognitive
Competence: New Approaches to Process Modeling. LEA. (in press)
- %AV ftp://ftp.cc.gatech.edu/pub/ai/simon/CompDev.tech.rtf
- %OR GTECH
- %LT GIT-CS-94/10
- %YR 1994
- %AB This chapter discusses the enterprise of building computational models
of developmental phenomena. We discuss what can be gained from
building such models and discuss the issues of modeling by decomposing
the process into the 3 sub-problems. These are, constructing a process
model of the behavior of interest, dealing with the self-modification
or learning processes and creating a plausible theory of environmental
input to the model. The chapter then reviews some issue in modeling of
special interest to developmentalists and finally previews the
chapters that comprise the edited volume it appears in.
- %TI Developing Cognitive Competence: New Approaches to Process Modeling
- %AU Tony J. Simon & Graeme S. Halford
- %PU Lawrence Erlbaum Associates. (In press)
- %AV ftp://ftp.cc.gatech.edu/pub/ai/simon/outline.txt
- %OR GTECH
- %YR 1994
- %AB Outline of the book along with chapter titles and authors.
- %TI Evidence for subitizing as a stimulus-limited processing phenomenon
- %AU Tony J. Simon & Angel Cabrera
- %PU Proceedings of 17th Annual Conference of the Cognitive Science Socitey
- %AV ftp://ftp.cc.gatech.edu/pub/ai/simon/simoncabrera.rtf
- %OR GTECH
- %YR 1995
- %AB We present an experiment where subject's subitizing performance for
linear dot arrays was analyzed using Differential Time Accuracy
Functions. This technique uses accuracy and reaction time data to
decompose overall response latency into stimulus-limited and
post-stimulus processing. Our results show that subitizing is a
phenomenon produced by the effects of increased numerosity on
stimulus-limited processes alone. They also suggest that the familiar
guessing strategy for the largest arrays in reaction time measures of
subitizing results from a reduction in post-stimulus
processing. Subjects appear to extract the perceptual characteristics
of all arrays but presumably fail for the largest and therefore
default to guessing. Existing theories of subitizing are evaluated in
light of these results.
- %TI Time-accuracy data analysis: Separating stimulus-limited and post-stimulus
processes
- %AU Angel Cabrera & Tony J. Simon
- %PU Proceedings of 17th Annual Conference of the Cognitive Science Socitey
- %AV ftp://ftp.cc.gatech.edu/pub/ai/simon/cabrerasimon.rtf
- %OR GTECH
- %YR 1995
- %AB Time-accuracy functions are obtained by measuring the accuracy of a
subject's responses at various levels of stimulus presentation
time. Unlike reaction time (RT) measurements, which convey
information about the entire set of processes taking place between the
onset of the stimulus and the production of a response, time-accuracy
functions (TAFs) focus on a subset of those processes, namely
stimulus-limited processes. Stimulus-limited processes are
responsible for the extraction of the perceptual information that is
necessary for the elaboration of a response. Post-stimulus processes
take care of selecting and executing the response based on the
information extracted by stimulus-limited processes. This paper
presents a method of analysis that allows us to (a) extract estimates
of the duration and variance of stimulus-limited processes from
individual TAFs and (b) combine these estimates with RT data in order
to induce the duration and variance of post-stimulus processes. The
method is illustrated with data from a subitizing (speeded
enumeration) task.