Tues/Thurs, 12:00 pm - 1:45 pm
Van Leer C340
Course web page: CS 4641 T-Square
Kaushik Subramanian, firstname.lastname@example.org
Office Hours: Thurs, 4:00 pm - 5:00 pm, and by appointment
Location: CCB 360B
Karl Gemayel, email@example.com
Office Hours: Mon/Fri, 11:00 am - 12:00 pm, and by appointment
Location: Klaus 1202
Machine Learning (ML) is that area of Artificial Intelligence that is concerned with computational artifacts that modify and improve their performance through experience. The area is concerned with issues both theoretical and practical. We will cover a variety of topics, including: statistical supervised and unsupervised learning methods, randomized search algorithms, Bayesian learning methods, and reinforcement learning. The course also covers theoretical concepts such as inductive bias, the PAC and Mistake-bound learning frameworks, minimum description length principle, and Ockham's Razor. In order to ground these methods the course includes some programming and involvement in a number of projects.
The primary objectives of the course:
To provide a broad survey of approaches and techniques in ML
To develop the skills that will help you to build intelligent, adaptive artifacts
To develop the basic skills necessary to pursue research in ML
Almost all ML applications today require you to think like a researcher. The last objective will be at the core of this course.
The official prerequisite for this course is an introductory course in artificial intelligence. CS 3600 or Peter Norvig and Sebastian Thrun's AI class on Udacity should suffice. Apart from this, the most important prerequisite for enjoying and doing well in this class is your interest in the material. If you are not sure whether this class is for you, please talk to me.
Readings. The textbooks for the course: 1) Machine Learning by Tom Mitchell and 2) Introduction to Machine Learning by Ethem Alpaydim. We will also use supplemental readings as well, but those will be provided for you.
Computing. Weblinks to ML toolboxes and datasets will provided for you (in the Resources tab). Also you are free to use whatever machines you want to do your work; however, the final result will have to run on the standard CoC boxes.
Web. We will use the Tsquare page to post course announcements, so check it early and often. We will also use Piazza to discuss course material offline. Course schedule is available in the Resources tab.
Your final grade is divided into four components: assignments, a group project, a midterm exam and a final exam.
Assignments. There will be two graded assignments. They will be about programming and analysis. Generally, they are designed to give you deeper insight into the material and to prepare you for the exams. The programming will be in service of allowing you to run and discuss experiments, do analysis, and so on.
Group Project. There is a semester-long group project. You will use it to pursue a topic of your interest in Machine Learning. At the end of the term, you will be required to produce a NIPS-style conference paper, and to give a short presentation. Along the way, your group will turn in a very short proposal and a somewhat longer progress report. The guidelines for the group project are provided in the Resources tab.
Midterm. There will be a written, closed-book midterm roughly halfway through the term.
Final Exam. There will be a written, closed-book final exam at the time that has been scheduled for our class' final exam.
Although class participation is not explictly graded, I will use your class participation to determine whether your grade can be lifted in case you are right on the edge of two grades. Participation means attending classes, participating in class discussions, asking relevant questions, volunteering to provide answers to questions, and providing constructive criticism and creative suggestions that improve the course.
All graded assignments are due by the time and date indicated. Late assignments are not accepted and there will be no make up exams. You will get zero credit for any late assignment. The only exceptions will require: a note from an appropriate authority and immediate notification of the problem when it arises. You should also treat assigned readings as assignments that are due at the beginning of each class.
You are all expected to follow the university's code of academic conduct (Honor Code).
Failure to cite your sources is an Honor Code violation. Unauthorized use of any previous semester course materials, such as tests, quizzes, homework, projects, and any other coursework, is prohibited in this course. Using these materials will be considered a direct violation of academic policy and will be dealt with according to the GT Academic Honor Code.
Learning about algorithms from text or online sources is permissible. Copying content verbatim from online or another student is not permissible.
Furthermore, copies of the exams are not allowed to be out in the ether (so there should not be any out there for you to use anyway). If you violate the policy in any shape, form or fashion you will be dealt with according to the GT Academic Honor Code.
Be honest in solving your assignments and exams and you will learn and enjoy the material.
The syllabus and course page should be considered a living document subject to change throughout the course of the semester. I reserve the right to modify any of these plans as need be during the course of the class; however, I won't do anything too drastic, and you'll be informed as far in advance as possible.