Artificial Intelligence - ECSE 526
course description
This course will introduce you to the field of AI, beginning from historical and philosophical perspectives, progressing through a number of core topics from classical AI, and then turning to various areas of machine learning (ML) including reinforcement learning, connectionist architectures (artificial neural networks) and evolutionary computing approaches.
questions
What will I learn?
Is this course for me?
Can I enroll in this course if I've already taken a CS course in AI or ML?
What's the workload like?
What computers do I use to run my assignments?
What's the text book?
What are the due dates and policy on late work?
How is my grade determined?
What are the in-class and homework activities?
Where's that line about academic integrity?
Further important information about the course is available from the course guide.
calendar
Note that this calendar view of the syllabus is intended only to serve as a rough guide, as it comes from a previous year's offering of the course.
Date Topic and slides Readings Videos Material Due weight
Sep. 3 Introduction: definitions, historical and philosophical underpinnings, and what this course is about Ch 1.1, | Littman, 'Rise of the Machines' is Not a Likely Future | Social Robots  
Sep. 8 Problem Solving By Search: problem formulation, search strategies, heuristics Ch. 3 |    
Sep. 10 Two-player games: minimax, alpha-beta pruning, position evaluators Ch. 5-5.4 | Patrick Winston. games, minimax and alpha-beta | Francisco Iacobelli. minimax tutorial  
Sep. 15 Intelligence and agency: agent classifications and architectures Ch. 2 | Brooks, A Robust Layered Control System for a Mobile Robot | Allyn, 'The Computer Got It Wrong' |  
Sep. 17 Probability Basics Ch. 13.2-13.5 Patrick Winston, lecture | Jeff Miller, tutorial on proportionality | Nando de Freitas, Bayes' Rule  
Sep. 22 Hidden Markov Models Ch. 15-15.3, interactive spreadsheet Jason Eisner, Probabilities and Language Models | Jeff Miller, part 1 | part 2  
Sep. 24 Decision Making: simple and complex decisions, Markov decision problems, utility, value iteration, policy iteration Ch. 16.3, 17-17.3    
Sep. 29 Principles of Machine Learning: regression, overfitting, training, validation, and test sets, leave-one-out cross-validation, k-fold cross-validation, gradient descent Ch 18-18.2 | Domingo, A Few Useful Things to Know about Machine Learning | Vincent, What a machine learning tool tells us about AI bias | | Jeff Miller, supervised learning | unsupervised learning  
Oct. 1 Inductive Learning: decision trees, pruning, ensemble learning, boosting Ch. 18.3 | Sammut et al., Learning To Fly Jeff Miller, decision trees  
Oct. 6 Non-parametric models: nearest neighbour, kd-trees, locally sensitive hashing Ch. 18.8 | Mitchell, Instance-based learning (pp. 230-234) Patrick Winston, lecture
Oct. 8 in-class game tournament
Oct. 13 Statistical Learning: Bayesian learning, MAP, maximum likelihood Ch. 20-20.2 Jeff Miller short tutorial  
Oct. 15 Mixture Models and Expectation Maximization Ch. 20.3 | Jeff Miller, EM algorithm | Why EM makes sense, part 1 | part 2  
Oct. 20 Passive Reinforcement Learning: direct utility estimation, adaptive dynamic programming, temporal difference learning Ch. 21-21.2 |  
Oct. 22 Active Reinforcement Learning: action-value function, Q-TD, exploratory learning, generalization Ch. 21.3-21.6 | Mahadevan & Connell, Automatic Programming of Behavior-based Robots using Reinforcment Learning |  
Oct. 27 k-means and PCA: clustering, component analysis, and dimensionality reduction PCA and Self-organizing maps | Jeff Miller, short tutorial  
Oct. 29 Constraint Satisfaction Problems Ch. 6-6.4    
Nov. 3 in-class game tournament
Nov. 5 Logical Agents: wumpus world, reasoning in propositional logic Ch. 7-7.5    
Nov. 10 Planning Ch. 10-10.2 | Sussman Anomaly Dolphin planning  
Nov. 12 Intro to Artificial Neural Networks Ch. 18.7 | Mitchell, Artificial Neural Networks (4.1-4.6) |
Schraudolph & Cummins, Introduction to NN | Tveter, BackProp Basics (or available as PDF here | Can animals deduce? (video) | Rowley, Baluja & Kanade, Neural-Network-Based Face Detection | Fels, An Adaptive Interface that Maps Hand Gestures to Speech |
Welch Labs, playlist  
Nov. 17 Neural Network Applications Pomerleau, Efficient Training of Artificial Neural Networks for Autonomous Navigation | OCHRE applet |  
Nov. 19 Evolutionary Computing: genetic algorithms, genetic programming, evolving neural networks Nolfi et al Phenotypic Plasticity in Evolving NN | Bling, MarI/O (video) | Koza, Breeding Populations of Programs to Solve Problems in AI |    
Nov. 24 recurrent neural networks, Boltzmann machines, networks, deep learning LeCun, Deep Learning | Kröse and van der Smagt, Intro to NN Ch. 5 | Hugo Larochelle, intro to deep learning
Nov. 26 Project Presentations  
Dec. 1 Project Presentations Project
Last updated on 29 August 2020