Intelligent Systems

Instructor

Fabio A. González
Maestría en Ingeniería de Sistemas y Computación
Universidad Nacional de Colombia

Course goal

Intelligent systems study the development of intelligent or rational agents. A rational agent must be able to act in order to maximize the best expected upcome. The goal of the course is to study the theory and methods that allow to build rational agents under different conditions.

1 Introduction

2 Problem Solving

2.1 Search

2.2 Adversarial search

2.3 Constraint satisfaction problems

3 Uncertain Reasoning

3.1 Probability

3.2 Probabilistic reasoning

3.3 Hidden Markov models

3.4 Markov decision problems

4 Learning

4.1 Supervised learning

4.2 Non-Supervised learning

4.3 Reinforcement learning

5 Perception and Communication

5.1 Computer vision

5.2 Natural language understanding

• Assignments 50%
• Exams 30%
• Final project 20%

Grades

References and resources

• [Russell10] Russell, S and Norvig, P. 2010 Artificial Intelligence: a Modern Approach, 3rd Ed, Prentice-Hall
• [Alp10] Alpaydin, E. 2010 Introduction to Machine Learning, 2Ed. The MIT Press.
• [AI-edX] CS188x_1 Artificial Intelligence, UC Berkley, edX,Fall 2013
• [Alp10] Alpaydin, E. Introduction to Machine Learning, 2Ed. The MIT Press, 2010
• [Sutton98] Sutton, R. and Barto, A. Reinforcement Learning: An Introduction, The MIT Press, 1998
• [aima-python] Python code for the book Artificial Intelligence: A Modern Approach, GitHub repository

Week	Topic	Material	Assignments
Feb 3	1. Introduction	[Russell10] Chap 1 (slides) and 2 (slides) [AI-edX] Introduction to AI (slides) (video)	[AI-edX] Math Self-Diagnostic [AI-edX] P0: Tutorial
Feb 10	2.1 Search	[Russell10] Chap 3 (slides) [AI-edX] Agents and Search (slides) (video) Search methods (Python notebook)
Feb 17	2.1 Search	[Russell10] Chap 3 (slides) [AI-edX] A* Search and Heuristics (slides) (video) Search methods (Python notebook)	Assignment 1
Feb 24	2.2 Adversarial search	[Russell10] Chap 5 (slides) [AI-edX] Game Trees: Minimax (slides) (video)	Adversarial search and games lab (Python notebook)
Mar 2	3.1 Probability	[Russell10] Chap 13 (slides) [AI-edX] Probability (slides) (video)
Mar 9	3.2 Probabilistic reasoning	[Russell10] Chap 14 (slides) [AI-edX] Bayes' Nets: Representation (slides) (video) [AI-edX] Bayes' Nets: Independence (slides) (video)
Mar 16	3.2 Probabilistic reasoning	[Russell10] Chap 14 (slides) [AI-edX] Bayes' Nets: Inference (slides) (video) [AI-edX]Bayes' Nets: Sampling (slides) (video) [Alp10] Chap 16 (slides)
Mar 30	3.3 Hidden Markov models	[Russell10] Chap 15 (slides) [AI-edX] HMMs: Filtering (slides) (video) [Alp10] Chap 15 (slides)	Assignment 2
Apr 6-13	4.1 Supervised learning	[Russell10] Chap 20 (slides) [AI-edX] ML: Naive Bayes (slides) (video) [Russell10] Chap 18 (slides) [AI-edX] ML: Perceptrons (slides) (video) [Alp10] Chap 11 (slides) Quick and dirty introduction to neural networks (IPython notebook)
Apr 20	4.2 Non-Supervised learning	[AI-edX] ML: Kernels and Clustering (slides) (video) [Alp10] Chap 7 (slides)	Assignment 3
Apr 27	4.3 Reinforcement learning	[Russell10] Chap 17 [AI-edX] Markov Decision Processes (slides) (video) [AI-edX] Markov Decision Processes II(slides) (video) [aima-python] Markov Decision Processes (notebook) (code)	[AI-edX] HW4
May 4	4.3 Reinforcement learning	[Russell10] Chap 21 [AI-edX] Reinforcement Learning (slides) (video) [AI-edX] Reinforcement Learning II(slides) (video) [Alp10] Chap 18 (slides) [Sutton98] (html) (pdf) [aima-python] Reinforcement Learning (notebook) (code)	[AI-edX] HW5