Artificial Intelligence

Boston University - Fall 2022

Class is held in CGS 527 on Tuesday and Thursday 2:00-3:15pm

Course staff and office hours

Wednesday 3-4pm, MCS 200C: Prof. Iddo Drori

Wednesday 12-1pm, MCS 103: Teaching Fellow, Sha (Stan) Lai

Grader, Siqi Wang

Grader, Yawed Gu

Textbooks

Artificial Intelligence: A Modern Approach, 4th Ed., Stuart Russell and Peter Norvig, Pearson, 2021

The Science of Deep Learning, Iddo Drori, Cambridge University Press, 2022

Enrolled students receive a free online version

First Day of Classes (Tuesday, September 6)

Part I

Lecture 1 (Tuesday, September 6): Introduction

Lecture 2 (Thursday, September 8): Neural networks

Lecture 3 (Tuesday, September 13): Neural networks

Lecture 4 (Thursday, September 15): Transformers

Lecture 5 (Tuesday, September 20): Transformers

Part II

Lecture 6 (Thursday, September 22): Markov decision processes

Lecture 7 (Tuesday, September 27): Reinforcement learning

Lecture 8 (Thursday, September 29): Reinforcement learning

Lecture 9 (Tuesday, October 4): Games

Lecture 10 (Thursday, October 6): Games

Part III

Lecture 11 (Thursday, October 13): Search

Lecture 12 (Tuesday, October 18): Search

Part IV

Lecture 13 (Thursday, October 20): Rule-based systems

Lecture 14 (Tuesday, October 25): Constraint satisfaction

Lecture 15 (Thursday, October 27): Trees

Lecture 16 (Tuesday, November 1): Bayesian networks

Lecture 17 (Thursday, November 3): Automated machine learning

Lecture 18 (Tuesday, November 8): Meta learning

Lecture 19 (Thursday, November 10): Logic

Part V

Lecture 20 (Tuesday, November 15): Winning the NeurIPS 2022 MineRL BASALT Challenge

Lecture 21 (Thursday, November 17): Artificial general intelligence

Lecture 22 (Tuesday, November 22): Artificial general intelligence

Thanksgiving recess, academic holiday, no classes (Wednesday, November 23 - Sunday, November 27)

Part VI

Lecture 23 (Tuesday, November 29): Applications

Lecture 24 (Thursday, December 1): Applications

Projects

Lecture 25 (Tuesday, December 6: Presentations

Lecture 26 (Thursday, December 8): Presentations

Last Day of Classes (Monday, December 12)

Exercises: quiz and programming homework

Exercise 1: Neural networks

Exercise 2: Convolutional neural networks

Exercise 3: Markov decision processes and RL

Exercise 4: Games and search

Exercise 5: Constraint satisfaction problems

Exercise 6: Bayesian networks

Exercise 7:

Exercise 8:

Exercise 9:

Exercise 10:

Labs

Lab 1: Python

Lab 2: Neural networks

Lab 3: Minecraft challenge

Lab 4: Markov decision processes

Lab 5: Reinforcement learning

Lab 6: Games

Lab 7: Search

Lab 8: Constraint satisfaction

Lab 9: Bayesian networks

Lab 10: Rule-based systems