Course Information
Text
AI: A Modern Approach, Stuart Russell and Peter Norvig, 2nd ed
(See below for additional readings)
(See below for additional readings)
Instructor
Prerequisites
ESO 211 Data Structures. Optional: Probability and Statistics, familiarity with logic.
Course Objective
Artificial Intelligence tries to have machines do
things that are normally associated with intelligence in humans. In the
process, this also sheds light on the processes of human cognition.
This course will introduce these topics through lectures, class presentations
and discussions, and most importantly, through projects. Each of you is
also expected to select a project in which you will investigate some
topic of current research interest, and you are expected to be able
to communicate the key ideas of your project to others in the course.
Grading Scheme
- Two Written Exams: 35%
- Course Discussions, Homework and Labs: 15-20%
-
Final Project: 45-50%
- Proposal: 5%
- Presentation: 10%
- Report: 15%
- Demo/Oral: 20%
Projects
- To be done in teams of 1 or 2 persons.
- Read and present a recent research paper from the list of suggested papers. Write a brief review. (around week 4)
- Define your project topic and present a project proposal. (around week 6)
- Implement the project over approximately six weeks.
- Projects from past years, assignments, solutions, and other details may be seen under the old course page.
- Owing to the high project weightage, project groups will be formed based on interest area groups based on the paper selected for review.
Course Topics
For some topic, there will be additional presentations by students.
| Topic | Week | References |
|---|---|---|
| INTRO: AI objectives and methods; agents: symbolic systems, learning systems | week 1 | ch.1,2 |
|
TURN to Learning: History of AI, Agent models: - Programmed intelligence : Symbolic processing - Learned behaviours: Abstracting from data - Embodied AI - developing symbols. |
week 2 | book ch.2, ch.18 |
| UNCERTAINTY : Probability; Classification and Regression; Probabilistic models; Information theory | week 3 | Ch. 13, Bishop ch.1, 18.2 |
| Mini-Workshop: State of AI : Proposal Presentations focusing on background and motivation | week 4 | Paper reviews based on list of papers |
| LEARNING: Decision Trees; Clustering; Generative vs Discriminative; Manifold Dimensionality Reduction; STATISTICAL LEARNING. Naive Bayes; k-NN; multi-layer perceptron; kernel methods & SVM; Deep Learning; | week 4-5 | ch. 13,18,20; Duda Hart ch.2; Bishop ch.1; |
| SENSING: Vision - Image Formation, Gradient and Motion cues, Learning Backgrounds, Tracking | week 6 | ch.24, Marr ch.1 |
| ACTION: Robotics - articulated and mobile robots; motion planning, task planning. | week 7 | ch.25 |
| SEARCH, CONSTRAINT PROPAGATION, and LOGIC: | week 8 | ch. 3, 5, 6 |
| LANGUAGE: natural language processing fundamentals | week 9 | ch.22, 23 ; ch. 26 |
| PROJECTS: proposal, presentations, final demos | weeks 10-12 | Relevent research papers |
| CLOSURE: cognitive science, philosophy, and the future | week 12b | ch.22, 23 ; ch. 26 |
Additional Readings
- Marr, David; Vision: A Computational Investigation Into the Human Representation and Processing of Visual Information, W.H. Freeman, 1982, 397 pages, ISBN 0716715678
- Bishop, Christopher M.; Pattern Recognition and Machine Learning, Springer, 2006, 738 pages, ISBN 0387310738
- Richard O. Duda; Peter E. Hart; David G. Stork; Pattern Classification (2/e), Wiley-India, 2007, 676 pages, ISBN 8126511168
- Lee, John A.; Michel Verleysen; Nonlinear Dimensionality Reduction, Springer 2007, 310 pages, ISBN 0387393501
- Research Papers