ECE 469: Artificial Intelligence

• Instructor Info
• Textbook
• Grading
• Projects
• Schedule

Instructor Info

Instructor: Carl Sable
e-mail: carl.sable@cooper.edu
Office: Room 614

Textbook

Grading

Projects and Problem Sets

• Problem Set #1
  Due by the start of class on Thursday, September 30
• Problem Set #2
  Due by the start of class on Tuesday, November 23
• Problem Set #3
  Due by the start of class on Thursday, December 16
• Project #1
  Due the night of Saturday, November 6, before midnight
  Click here for a suggested schedule and other helpful information
  Click here for a readme file briefly describing the files provided below
  Click here to download my Checkers executable (compiled under Cygwin)
  Click here to download my Othello executable (compiled under Cygwin)
  Click here for cygwin1.dll (if you need it; see the readme)
  Click here for cygstdc++-6.dll (if you need it; see the readme)
  Click here for cyggcc_s-seh-1.dll (if you need it; see the readme)
  Click here to download my Checkers executable (compiled under Ubuntu 20.04)
  Click here to download my Othello executable (compiled under Ubuntu 20.04)
  Sample Checkers board #1
  Sample Checkers board #2
  Sample Checkers board #3
  Sample Checkers board #4
  Sample Checkers board #5
  Sample Checkers board #6
  Sample Checkers board #7
  Sample Checkers board #8
  Sample Checkers board #9
  Sample Checkers board #10
  Sample Othello board #1
  Sample Othello board #2
• Project #2
  Due the night of Tuesday, December 7, before midnight
  Click here for my annotated version of Figure 18.24 from the 3rd edition of the textbook
  Click here for the raw data of the Wisconsin Diagnostic Breast Cancer (WDBC) dataset
  Click here for a description of the data set by its creators
  Click here for my pre-processed WDBC training set file
  Click here for my pre-processed WDBC test set file
  Click here for my initial neural network for the WDBC dataset
  Click here for my trained neural network for the WDBC dataset
  (with a learning rate of 0.1 after 100 epochs)
  Click here for my results file (using the above trained neural network)
  Click here for a mini WDBC training set with one document (to help with debugging)
  Click here for the neural network trained on the mini WDBC training set
  (with a learning rate of 0.1 after 1 epoch)
  Click here for my grades training file
  Click here for my grades test file
  Click here for my initial neural network for the grades dataset
  Click here for my trained neural network for the grades dataset
  (with a learning rate of 0.05 after 100 epochs)
  Click here for my results file (using the above trained neural network)

Schedule

Part 1: Introductory Concepts

• Wednesday, September 1
  Topic: Course Introduction (slides)
  Suggested Reading: R&N Chapter 1
• Thursday, September 2
  Course Introduction (continued)
  Topic: Intelligent Agents (slides)
  Suggested Reading: R&N Chapter 2

• Wednesday, September 8
  Topic: Simple Search Strategies (slides)
  Suggested Reading: R&N Sections 3.1 - 3.4 and 4.4.1
• Thursday, September 9
  Simple Search Strategies (continued)
• Wednesday, September 15
  Topic: Advanced Search Strategies (slides)
  Suggested Reading: R&N Sections 3.5 - 3.6, 4.1 - 4.2, and 4.5
• Thursday, September 16
  Advanced Search Strategies (continued)
• Wednesday, September 22
  Topic: Games (slides)
  Suggested Reading: R&N Chapter 5
• Thursday, September 23
  Games (continued)
• Wednesday, September 29
  Games (continued)
• Thursday, September 30
  Games (continued)
• Wednesday, October 6
  Project #1 assigned and discussed

• Thursday, October 7
  Topic: Probability (slides)
  Suggested Reading: R&N Chapter 12
• Wednesday, October 13
  Topic: Bayesian Networks (slides)
  Suggested Reading: R&N Chapter 13
• Thursday, October 14
  Topic: Bayesian Networks (continued)
• Wednewsday, October 20
  Topic: Hidden Markov Models (slides)
  Suggested Reading: R&N Sections 14.1 - 14.3 and "An Introduction to Hidden Markov Models and Bayesian Networks" (Ghahramani 2001)

• Thursday, October 21
  Topic: Machine Learning Concepts (slides)
  Suggested Reading: R&N Sections 19.1 - 19.2 and 19.4
  Topic: Decision Trees (slides)
  Suggested Reading: R&N Section 19.3
• Wednesday, October 27
  Decision Trees (continued)
• Thursday, October 28
  Topic: Bayesian Learning (slides)
  Suggested Reading: R&N Chapter 20
• Wednesday, November 3
  Topic: Feedforward Neural Networks (slides)
  Suggested Reading: R&N Sections 21.1 - 21.2
  Click here for my annotated version of Figure 18.24 from the 3rd edition of the textbook
• Thursday, November 4
  Feedforward Neural Networks (continued)
• Wednesday, November 10
  Topic: Deep Neural Networks (slides)
  Suggested Reading: R&N Sections 21.3 and 21.5
• Thursday, November 11
  Topic: Non-parametric Machine Learning (slides)
  Suggested Reading: R&N Sections 19.7.1 and 19.7.5-19.7.6
  Project #2 assigned and discussed

• Wednesday, November 17
  Topic: Conventional Statistical Natural Language Processing (slides)
  Suggested Reading: R&N Section 23.1
• Thursday, November 18
  Conventional, Statistical Natural Language Processing (continued)
• Tuesday, November 23 (Thursday Schedule)
  Topic: Conventional Computational Linguistics (slides)
  Suggested Reading: R&N Sections 23.2 - 23.6
• Wednesday, December 1
  Conventional Computational Linguistics (continued)
• Thursday, December 2
  Topic: Deep Learning and NLP (slides)
  Suggested Reading: R&N Chapter 24
• Wednesday, December 8
  Deep Learning and NLP (continued)

• Wednesday, December 15
  Topic: Philosophy and Ethics of AI (slides)
  Suggested Reading: R&N Chapter 26 and "Computing Machinery and Intelligence" (Turing, 1950)
• Thursday, December 16
  Philosophy and Ethics AI (continued)