Artificial Intelligence Educational Curriculum

College of Computing, Georgia Tech

Educational Programs

Breadth and Depth Requirements

Financial Aid

Graduate research and teaching assistantships are available. Assistantships are awarded on the basis of academic promise. Students with excellent credentials are also eligible for Institute-wide fellowships.

Applications

To find out more about the graduate programs in the College of Computing, and to request application materials and research brochures, send e-mail to , or write to the Office of Student Services, College of Computing, Georgia Institute of Technology, Atlanta, Georgia 30332-0280.

Course Numbering Scheme

    Number      Type

    3000        basic undergraduate
    4000        advanced undergraduate
    5000        undergraduate, remedial graduate
    6000        basic graduate
    7000        core advanced ai courses
    8000        advanced seminars/special topics/research topics/etc.

    Number      Area

    x33x        problem solving
    x34x        conceptual information processing/natural language/learning
    x35x        cognitive science
    x36x        core AI, AI programming, misc AI
    x37x        vision/robotics

List of Courses

Click on the name of any course or instructor for more information.

CS 3361. Introduction to Artificial Intelligence.
Introduction to fundamental topics in artificial intelligence, including cognitive modelling, knowledge representation and inference, search, problem solving and planning, natural language processing, learning, expert systems, vision, and robotics. AI Faculty.

CS 4324. Intelligent Robotics and Computer Vision.
Methodologies for embedding artificial intelligence in robotic systems. Topics include robot task and assembly planning, autonomous navigation, sensor-based robotic systems, supporting low-level visual processing, perceptual organization, and model-based vision. Arkin.

CS 4331. Problem Solving and Learning.
Fundamental concepts and methods in knowledge-based problem solving and learning, including knowledge representation and organization, planning, knowledge-based systems, knowledge acquisition, example-based learning and explanation-based learning. Goel.

CS 4344. Natural Language Understanding By Computer.
Methodologifes for designing systems that comprehend natural language. Topics include lexical analysis, parsing, interpretation, and generation of sentences; semantic representation, organization of knowledge, and inference mechanisms. Eiselt.

CS 4361. Design Project in Artificial Intelligence.
Directed study with individual faculty on specialized projects in AI, including the design and development of a software AI system. AI Faculty.

CS 4730. Lisp Programming for Artificial Intelligence.
Introduction to computer programming in Common LISP, with a focus on preparing the student for using Common LISP and AI programming techniques to solve problems in AI. Eiselt.

CS 6361. Artificial Intelligence.
Graduate level introductory course in AI, covering several topics ranging from knowledge representation, planning, search, and other fundamental of AI, to selected topics in natural language processing, learning, problem solving, computer vision and robotics. AI Faculty.

CS 6362. Applications of Artificial Intelligence.
Introduction to real world applications of AI. Topics include robotics, computer vision, expert systems, and neural networks. Not for CS Ph.D. students. Arkin.

CS 6364. Hypermedia.
Introduction to hypermedia tools, methods and design. Lawton.

CS 7321. Low Level Computer Vision.
Introduction to computer vision and machine perception, and extracting symbolic and environmental information from images. Topics include paradigms, feature extraction, perceptual organization, perspective, motion, stereo, color, and texture. Lawton.

CS 7322. High Level Vision.
Machine vision systems using AI and model-based techniques. Topics include architectures, object models, indexing and matching, hypothesis and uncertainty management, constraints, and active sensing. Lawton.

CS 7323. Autonomous Robotics.
Designing intelligent autonomous robotic systems, with a special emphasis on neuroscientific and cognitive models of behavior. Arkin.

CS 7331. Problem Solving.
Fundamental concepts and methods in knowledge-based problem solving, including knowledge representation and organization, planning, inference mechanisms, control architectures, design, explanation, and knowledge acquisition. Goel.

CS 7332. Case-Based Reasoning.
Case-based reasoning is a kind of analogical reasoning and an alternative method for building expert systems. Topics include case representation, indexing, and retrieval, adaptation, interpretive case-based reasoning, the cognitive model case-based reasoning implies, and its implications for creativity, decision aiding, and education. Kolodner.

CS 7341. Conceptual Information Processing.
In-depth introduction to the conceptual approach to language, understanding, inference and reasoning. Topics include knowledge representation, inference and causality, conceptual analysis of natural language, story generation, explanation, memory, learning and integrated processing. Kolodner, Eiselt, Ram.

CS 7342. Knowledge Structures for Machine Intelligence.
A study of the knowledge and inferences necessary for understanding and problem solving; knowledge organization; representation of episodes; question answering; reconstructive memory. Kolodner.

CS 7343. Machine Learning.
Fundamental issues in Machine Learning, including the algorithmic, psychological, philosophical and methodological foundations of the field. Topics include empirical or inductive learning, concept learning, learnability theory, analogical and case-based learning, and explanation-based learning. Ram.

CS 7344. Natural Language Understanding.
Methodologies for designing systems that comprehend natural language. Topics include lexical analysis, parsing, and interpretation of sentences; semantic representation; organization of knowledge; and inference mechanisms. Eiselt.

CS 7360. Advanced AI System Development.
Study of advanced programming methodologies for AI, including data-driven programming, agenda control, deductive information retrieval, discrimination networks, production systems, frames, and chronological and dependency-directed backtracking. AI Faculty.

CS 8011. Extremely Weighty Issues in Artificial Intelligence.
The AI seminar is an on-going research seminar attended by faculty and students in and interested in AI and Cognitive Science. Faculty and students present research questions, discuss research issues, defend research claims, and critique research theories. Presentations are lively and discussion-oriented with active audience participation. Ram.

CS 8011. Current Research in Learning.
Learning is a central area of research in both artificial intelligence and psychology. In this seminar, we read recent research papers in and related to machine and human learning. We discuss current topics and issues for research, and survey recent results in the field. The seminar covers a broad range of topics, while focussing on the interests of the students and faculty attending the seminar. Ram.

CS 8011. Computational Models of Human Language Comprehension
Seminar on cognitive and computational models of natural language understanding. Discussion topics include processes of language comprehension, types of knowledge required, and frameworks for describing and evaluating models. Eiselt.

CS 8011. Knowledge Representation and Reasoning.
Reading and discussion of selected topics, issues, and views in artificial intelligence, focusing on mental models, design, and learning. Goel.

CS 8050. Proseminar in Cognitive Science.
Introduction to cognitive science, emphasizing interdisciplinary approaches to issues in cognition including memory, language understanding, problem solving, learning, perception, and action. Kolodner.

CS 8051. Issues in Cognitive Science.
Introduction to current issues in Cognitive Science by reading research papers by leading cognitive scientists, attending colloquia given by invited speakers, and meeting the speakers to discuss research. The course runs in conjunction with the Cognitive Science Colloquium series. AI Faculty.

CS 8113R, ISyE 8100B, LCC 6003B. Educational Technology.
Survey of existing theoretical approaches to learning, specific technologies, and resulting interaction styles. Topics include microworlds, constructionism, intelligent tutoring systems, student modelling, interactive learning environments, coaching/apprenticeship learning, collaborative learning, multimedia/hypermedia. Recker, Govindaraj.

CS 8113. Design and Analysis of Educational Software.
Focus on the issues surrounding (1) designing educational software (e.g., content, structure, educational philosophy, making it work in school cultures) and (2) analyzing that software in actual use (e.g., issues of gathering data in real classrooms, analyzing log file data). Guzdial.

CS 8113N, LCC 5791, PSY 7011B. Cognitive Perspectives.
The focus of the course will be on cognitive models of science proposed by philosophers. We will address such questions as : by constructing cognitive models can we better understand how scientists devise and execute real world and thought experiments, construct arguments, create concepts, invent and use mathematical tools, communicate ideas and practices, and train practitioners? Can theories and methods in the cognitive sciences provide a means for reconstructing historical "discovery processes"? What area(s) of cognitive science offer the most potnetial for fruitful analyses: AI, psychology, cognitive neuroscience? What is the relation between cognitive and social models of science? Nersessian.

For more information:
Human contact point