No other
field in computer science has higher visibility (and expectation, and disappointment)
than artificial intelligence to the general population. This course
covers some advanced components of artificial intelligence as we know it,
namely deductive reasoning agents, reactive agents, probabilistic
reasoning and Bayesian networks. You should be able to build an
example of a probabilistic model at the end of the semester.
Here you will find administrative information for the Fall 1398.
Instructor: Dr. Mohsen Afsharchi, afsharchi at znu.ac.ir
Lectures: 3-5 Sat
and 8-10 Wed
Prerequisites: Clear understanding of
probability, common data structures, algorithms, standard programming and
preferably some preliminary AI concepts.
Some
useful textbooks for this course are:
1. Bayesian Networks and Decision Graphs, (Second
Edition), by Finn V. Jensen and Thomas D. Nielsen, Springer 2007
2. Artificial Intelligence: A Modern Approach
(Third Edition), by Stuart J. Russell, Peter Norvig, Prentice Hall 2010 .
3. An
Introduction to Multiagent Systems , (Second Edition), by Michael
Wooldridge, Wiley 2009
Lecture
material will be drawn from textbooks, as well as from some of the recent
online materials.
- Introduction to AI: history (PDF), (AI Brain)
- Uncertainty in AI: Non-monotonic Reasoning, Certainty Factor, Probabilistic Models (PDF), The Mechanization of Causal Inference: A "Mini Turing Test" and Beyond (Video)
- Introduction to Probability theory: Basics (PDF)
- Probabilistic Graphical Models: Causal and Bayesian Networks (PDF)
- Building Models: Variables, Arcs and Dependencies (PDF)
- Inference in Bayesian Network 1: Variable Elimination Algorithm(PDF, Courtesy of Eyal Amir)
- Inference in Bayesian Network 2: Approximate Inference (PDF)
- Markov Processes: Markov Models, Hidden Markov Models(PDF)
- Markov Models: Applications: (PDF, Courtesy of Jan Rupnic )(Markov Chain Interpretation of Google Page Rank, PDF ,PDF)
- Hidden Markov Models: (Particle Filtering, PDF)
- Markov Decision Process: (PDF) Reading Material (Scalable MDP Based Planning...)
- Reinforcement Learning: (PDF)
Homework 1 (PDF) (RiskFactorData.csv)
Homework 2 (PDF)
Homework 3 (PDF)