CS 440

Web Page

https://courses.engr.illinois.edu/cs440/fa2023/

Official Description

Major topics in and directions of research in artificial intelligence: basic problem solving techniques, knowledge representation and computer inference, machine learning, natural language understanding, computer vision, robotics, and societal impacts. Course Information: Same as ECE 448. 3 undergraduate hours. 3 or 4 graduate hours. Prerequisite: CS 225; one of CS 361, STAT 361, ECE 313, MATH 362, MATH 461, MATH 463, STAT 400 or BIOE 310.

Course Director

Margaret M Fleck
Julia Constanze Hockenmaier

Text(s)

Artificial Intelligence a Modern Approach, 3rd E., by Stuart Russell and Peter Norvig

Learning Goals

Master the theoretical issues and principles underlying AI systems and use this understanding to analyze novel AI systems. (1), (6)
Design and implement illustrative AI systems (2)
Judge realistic vs. unrealistic claims for AI in the popular press, and evaluate the likelihood of success of hypothetical applications of AI as components of larger computer systems. (1)

Topic List

World modeling with symbolic and statistical representations:
First-order logic, formal inference, the qualification problem
Random Variables & Distributions, Conditional independence, Bayes &Markov nets, Parameter estimation
Tradeoffs among expressiveness, efficiency, accuracy, & robustness
Sequential decision making: Classical planning, Reinforcement learning, Markov decision processes
Machine learning:
Supervised, unsupervised, semi-supervised
Linear classifiers: Perceptrons, Naïve Bayes, Logistic regression
Nonlinear classifiers: Neural networks, Support vector machines & kernel methods
Computational learning theory: learnability, VC analysis
Statistical learning theory: error bounds, regularization
AI Applications: NLP, vision, search engines, data mining, collaborative filtering
Social & philosophical implications

Assessment and Revisions

Revisions in last 6 years	Approximately when revision was done	Reason for revision	Data or documentation available?	Documentation provided?
Increased coverage of Support Vector Machines & kernel methods	Fall 2008	Reflect importance of the topic in the field	Informal discussions	None
Introduce Markov blanket; less emphais on D-Separation	Fall 2010	Reflect new & simplified text treatment	Informal discussions	None
Included Statistical Learning Theory as a separate topic; less emphasis on Computational Learning Theory	fall 2010	Stay current with field	Informal discussions	None
Increase focus statistical methods while decreasing emphasis of symbolic methods	On-going	Stay current with field	Informal discussions	None

Required, Elective, or Selected Elective

Selected Elective.

Last updated

2/3/2019by Margaret M. Fleck