This is an old revision of the document!
Sept 7: Assignment 2 is now complete.
Aug 31: Assignment 1 now includes another example.
Lecture videos are available from the Canvas site (in the menu on the left) by selecting Echo 360.
To use jupyter notebooks on our CS department machines, you must add this line to your .bashrc file:
| Week 1:|
Aug 21 - Aug 25
| What is AI? Promises and fears.|
| 01 Introduction to AI|
02 Introduction to Python
03 Problem-Solving Agents
| Chapters 1, 2, 3.1.|
AI, People, and Society, by Eric Horvitz.
Automated Ethics, by Tom Chatfield.
The Great A.I. Awakening, by Gideon Lewis-Krause, NYT, Dec 14, 2016.
"Fundamental Existential Threat": Lawmakers Warned of the Risks of Killer Robots, by Julia Conley
Section 1 of Scipy Lecture Notes
| Week 2:|
Aug 28 - Sept 1
| Problem-solving search and how to measure performance.|
Iterative deepening and other uninformed search methods.
| 04 Measuring Search Performance|
05 Iterative Deepening and Other Uninformed Search Methods
06 Python Implementation of Iterative Deepening
|Sections 3.1 - 3.4|
| Week 3:|
Sept 4 - Sept 8
|Informed search. A* search. Python classes, sorting, numpy arrays.|| 07 Informed Search|
08 Python Classes
|Rest of Chapter 3|| A1 Uninformed Search due Tuesday, September 5th, at 10:00 PM.
Here are examples of good A1 notebooks: a, b, c, d, e, f, g
| Week 4:|
Sept 11 - Sept 15
| A* optimality, admissible heuristics, effective branching factor.|
Local search and optimization.
|09 Heuristic Functions|
10 Local Search
|Chapter 4|| A2 Iterative-Deepening Search due Thursday, September 14th, at 10:00 PM.
| Week 5:|
Sept 18 - Sept 22
|Adversarial search. Minimax. Alpha-beta pruning. Stochastic games.||11 Adversarial Search||Chapter 5|
| Week 6:|
Sept 25 - Sept 29
|Negamax, with pruning.|| 12 Negamax|
13 Modern Game Playing
|A3 A*, IDS, and Effective Branching Factor due Friday, September 29th, at 10:00 PM.|
| Week 7:|
Oct 2 - Oct 6
|Introduction to Reinforcement Learning.||14 Introduction to Reinforcement Learning|| Chapter 21|
Reinforcement Learning: An Introduction
| Week 8:|
Oct 9 - Oct 13
| Reinforcement Learning for Two-Player Games.|
Introduction to Neural Networks
| 15 Reinforcement Learning for Two-Player Games|
16 Introduction to Neural Networks
|Sections 18.6 and 18.7||A4 Negamax with Alpha-Beta Pruning and Iterative Deepening due Wednesday, October 11th, at 10:00 PM.|
| Week 9:|
Oct 16 - Oct 20
|More Neural Networks||17 More Introduction to Neural Networks|
| Week 10:|
Oct 23 - Oct 27
|Introduction to Classification. Bayes Rule. Generative versus Discriminative. Linear Logistic Regression.||18 Introduction to Classification||A5 Reinforcement Learning Solution to Towers of Hanoi due Wednesday, October 25th, at 10:00 PM.|
| Week 11:|
Oct 30 - Nov 3
|Classification with Neural Networks|| 19 Classification with Linear Logistic Regression|
20 Classification with Nonlinear Logistic Regression Using Neural Networks
|Project Proposal due Wednesday, November 1st, at 10:00 PM.|
| Week 12:|
Nov 6 - Nov 10
| Reinforcement Learning with Neural Networks.|
Lecture and Chuck's office hours on Thursday are cancelled. He will be out of town.
|21 Reinforcement Learning with a Neural Network as the Q Function|
| Week 13:|
Nov 13 - Nov 17
|Faster Reinforcement Learning. Autoencoder neural networks.||22 Autoencoder Neural Networks||A6 Neural Networks due Friday, November 17th, at 10:00 PM.|
|Nov 20 - Nov 24||Fall Break|
| Week 14:|
Nov 27 - Dec 1
|Constraint satisfaction. Min-conflicts|| 23 Constraint Satisfaction Problems|
24 Min-Conflicts in Python with Examples
| Chapter 6.|
A new iterated local search algorithm for solving broadcast scheduling problems in packet radio networks
| Week 15:|
Dec 4 - Dec 8
| Recurrent neural networks and use in natural language|
Dec 7, Thursday, PLEASE ATTEND. Course Surveys will be filled out.
|25 Natural Language|
| Finals Week:|
Dec 11 - Dec 15
| Final Project notebook is due Tuesday, Dec 12th, 10:00 pm. Here is a simple example.
Here is a list of links to almost everyone's final reports