The schedule below represents my current best estimate concerning due dates (and everything else). I am providing this information to give you a general idea of the pace and timing of the class. This schedule will certainly change as the semester progresses.
Unless otherwise noted, all readings are from Artificial Intelligence: A Modern Approach. Stuart Russell and Peter Norvig, Prentice Hall, 2009. Readings followed by (S) are supplemental. You should read them, but you won't be tested on that material.
| WEEK | DATE | TOPIC | READING | OUT | IN |
| 1 | 08-27 | Introduction/Syllabus (.pdf) | Ch. 1 | HW1 | |
| 08-29 | Uninformed Search (.pdf) | Python Tutorial 2-2.3 (skim) 3-3.4 Appendix A.1.2 |
HW2 | ||
| 08-31 | Uninformed Search (.pdf) Search Exercise (.pdf) |
HW3 | |||
| 2 | 09-03 | Discuss Turing Paper | Computing Machinery and Intelligence 26.1-26.2 (S) |
PA1 | HW1 |
| 09-05 | Informed Search (.pdf) | 3.5 - 3.6 | HW2 | ||
| 09-07 | Minimax (.pdf) | 5 - 5.3 | HW3 | ||
| 3 | 09-10 | Finish Adversarial Search CSPs |
5.4-5.5, 5.7 6-6.1, skim 6.2-6.3 |
HW4 | |
| 09-12 | Propositional Logic (.pdf) | 7 - 7.5.1 | |||
| 09-14 | Resolution | 7.5.2-7.5.4 Skim 7.6-7.8 |
HW4 | ||
| 4 | 09-17 | First Order Logic (.pdf) | 8—8.2 | PA1 - Checkup | |
| 09-19 | Inference in First Order Logic | Skim 8.3-8.5 9-9.4 |
hw5.pdf hw5.tex |
||
| 09-21 | Prolog Activity | Prolog Intro | |||
| 5 | 09-24 | Linear Algebra and Numpy | Appendix A.2 Numpy Tutorial (S) |
PA2 | PA1 |
| 09-26 | Gradient Descent | 4.2 | HW5 | ||
| 09-28 | Linear Regression | 18.6 - 18.6.2 | |||
| 6 | 10-01 | Logistic Regression linear_regression.py |
18.6.3-18.7 | ||
| 10-03 | Numpy (In CS/ISAT 250) | Numpy Tutorial (S) | HW6 (.pdf) linalg_hw6.py logistic_regression.py usps.npy |
||
| 10-05 | Neural Networks (.pdf) | ||||
| 7 | 10-08 | Neural Networks + Tuning (.pdf) |
18-18.2, 18.4 | ||
| 10-10 | HW6 Review | HW6 | |||
| 10-12 | Non-Parametric Learning | 18.8 | PA2 | ||
| 8 | 10-15 | Midterm Review | |||
| 10-17 | MIDTERM | ||||
| 10-19 | Support Vector Machines | 18.9 | |||
| 9 | 10-22 | Probability (.pdf) | 13-13.3 | ||
| 10-24 | Bayes Classifier (.pdf) | 13.4-13.5 | hw7.pdf hw7.tex |
||
| 10-26 | Bayes Nets (.pdf) Bayes Net Demo (.html) |
14-14.3, Skim 14.4-14.5 | PA3 | ||
| 10 | 10-29 | Hurricane Day | |||
| 10-31 | Learning in Probabilistic Models (.pdf) | 20-20.2 | |||
| 11-02 | Continue Learning | HW7 | |||
| 11 | 11-05 | Hidden Markov Models (.pdf) | 15-15.3, Skim 20.3 | ||
| 11-07 | Hidden Markov Models | ||||
| 11-09 | Hidden Markov Models | Poster Topic | |||
| 12 | 11-12 | MDP's (.pdf) | 16.1-16.2, 17.1-17.2 | PA4, (Q1-Q3) HW8 |
PA3 |
| 11-14 | Finish MDP's Value Iteration Demo |
||||
| 11-16 | Reinforcement Learning (.pdf) Q-Learning Demo |
21-21.3 | |||
| 13 | 11-19 | THANKSGIVING BREAK | |||
| 11-21 | THANKSGIVING BREAK | ||||
| 11-23 | THANKSGIVING BREAK | ||||
| 14 | 11-26 | Genetic Algorithms (.pdf) GA Demo |
4.1 | hw9.pdf hw9.tex |
HW8 |
| 11-28 | Work Day | Poster Bibliography |
|||
| 11-30 | Ethical Issues | 26 - 26.4 | |||
| 15 | 12-03 | Poster Session | |||
| 12-05 | Poster Session | ||||
| 12-07 | Review for Final | PA4, HW9 |