CS 687
Advanced Aritificial Intelligence

Time/Location: Monday 7:20-10pm, Innovation Hall 204
Instructor: Jana Kosecka
Office hours: Wednesday 2-3pm
Contact: Office 4444 Research II, e-mail: kosecka@gmu.edu, 3-1876
Course web page: http://www.cs.gmu.edu/~kosecka/cs687/

Required Textbook:
[1] Russel and Norvig: Artificial Intelligence: A Modern Approach, 2nd edition
[2] Russel and Norvig: Artificial Intelligence: A Modern Approach, 3rd edition
[3] Sutton and Barto: Reinforcement Learning: An Introduction

Announcements
Readings and Project Information
Piazza

Schedule (subject to change)


Date Topic, Handouts Assignments/Due dates Resources
week 1, January 28th Introduction and course logistics slides.pdf
Intro to Machine Learning, regression notes.pdf
Linear Algebra Review notes.pdf
Get familiar Matlab; Read Stanley paper (.pdf)
  Ch. 18, 20.5
week 2, Feb 4 Classification, Logistic Regression
HW1 , notes from prev. week, [1], Chap 20.5 Neural nets, [2] Chap 18.6-18.7 Logistic Regression Additional Resources
week 3, Feb 11 Perceptron, Neural Nets, slides
Instance Based Learning slides
Ch 18.7-18.8 HW1 Part 2 Deep Learning, Tutorials, Repositories
week 4, Feb 18 Unsupervised Learning, EM, Dimensionality Reduction (face recognition PCA slides), Spectral Clustering HW1 due, 20.3. (Clustering) Spectral Clustering paper , EM handout ,
week 5, Feb 25 Ensemble Methods, Support Vector Machines slides, Modelling Uncertainty, Naive Bayes slides, HW2 , Ch 18.9-18.10 (SVM, Ensemble), Ch 20.6, 13.1-13.6, Ch 14.1 - 14.5 Face Detection , Pedestrian Detection
week 6, March 4 Bayes Nets, Semantics Syntax, Reasoning Patterns, Inference by enumeration slides Ch 20.6, 13.1-13.6, Ch 14.1 - 14.5 HW2 due, HW3 , HW2 solution
week 7, March 11 Spring Break
week 8, March 18 Inference by Sampling (lect 6 cont), Hidden Markov Models tutorial , lecture slides Ch 15.1-15.3 , HW3 due, HW4 out , HW3 solution ,
week 9, March 25 Kalman Filters slides Ch. 25, 23 Ch 15.1-15.6, Project Proposal Due March 29 (via e-mail or drop off) ,
week 10, April 1 Bayes Filters in Robotics slides
Markov Decision Processes slides
Ch. 25, 23, Ch. 17, HW 4 due
week 11, April 8 Guest Lecture Intro , Evolutionary Computation Design Exam out April 7, Exam due April 8 in class
week 12, April 15 Partially Obervable Markov Decision Processes, Reinforcement Learning slides Ch 17, Ch 21
week 13, April 22 POMDP's, Continuous MDP's (continued), slides
PageRank Algorithm slides
Ch 17, Ch 21
week 14, April 29 Planning slides , Natural Language Processing Ch 10, Ch 22 Project Presentation Guidelines slides
week 15, May 6 Vision, Perception, slides , project guidelines Ch 24
May 13 Final Project Presentation, In class
formatting instructions latex (.tar.gz) MS word (.doc)

Related resources

Matlab resources - Matlab Primer