Following is the tentative schedule of classes and labs before Spring Break, roughly the first half of the semester.
| Date | Reading | Topic | Due |
|---|---|---|---|
| 2/7 | Overview of the course | ||
| 2/9 | Chap 1 | Introduction to machine learning | |
| 2/11 | Chap 1 | More general comments on machine learning | |
| 2/14 | Discussion of LMS homework project | ||
| 2/16 | More discussion of project | ||
| 2/18 | Sect. 2.1-2.4 | Introduction to concept learning; Find-S algorithm | |
| 2/21 | 2.5-2.8 | Version spaces, candidate elimination, and inductive hypotheses | |
| 2/23 | 3.1-3.4.1.1 | Decision trees as hypotheses; basic ID3 algorithm for concept learning | |
| 2/25 | Finish 3.4 | Entropy and information gain; a closer look at ID3 | |
| 2/28 | 3.5-3.6 | Hypothesis space search and inductive bias in decision tree learning | Lab #1 |
| 3/1 | 3.7 | Lab day | |
| 3/3 | 4.1-4.4 | Introduction to artificial neural networks; perceptrons | Homework #1 |
| 3/6 | 4.4 | Delta training rule for Perceprtons | |
| 3/8 | Lab day | ||
| 3/10 | 4.5 | Multi-layer networks and back-propogation | |
| 3/13 | 4.5 | More about back-propogation | Lab #2 |
| 3/15 | 4.7 | An illustrative example: face recognition | |
| 3/17 | Lab day | ||
| 3/20 | 4.6 & 4.8 | Yet more about back-propogation; advanced topics in ANN | |
| 3/22 | 9-9.3 | Genetic algorithms with an illustrative example | |
| 3/24 | Another example application of genetic algorithms | Lab #4 | |