All the lecture notes will be linked to this web page, in PDF and postscript format. The reader for PDF files is available free from Adobe for UNIX, Apple Macintosh, and Windows. You can view both postscript and PDF files using ghostview. For printing convenience, I am including 2 slides per page. I am happy to release tex source files or postscript/PDF for the actual slides on request..
| Introduction | Mitchell, Chapter 1 Slides: PS, PDF |
|||
| Concept Learning and Version Spaces | Mitchell, Chapter 2 Slides: PS, PDF |
|||
| Bayesian Learning | Mitchell, Sections 6.1-6.4, 6.7-6.10 Slides: PS, PDF |
PS, PDF |
||
| Basics of Information Theory. Decision Trees | Mitchell, Chapter 3 Slides: PS, PDF |
|||
| Decision Trees. Overfitting | Mitchell,
Chapter 3, Section 6.6 Slides: PS, PDF | |||
| Aritificial Neural Networks - I | Mitchell, Chapter 4 Slides: |
|||
| Artificial Neural Networks - II | Mitchell, Chapter 4 Slides: PS, PDF |
|||
| Empirical Evaluation | Mitchell, Chapter 5 |
PS, PDF C4.5 web page UCI Repository |
||
| No lecture |
|
|||
| PAC-Learning | Mitchell, Sections 7.1-7.3 Slides: PS, PDF |
PS, PDF Book code and data |
||
| VC Dimension | Mitchell, Section 7.4 Slides: PS, PDF |
|
||
| Instance-based Learning | Mitchell, Chapter 8 Slides: PS, PDF |
|||
| Ensemble Classifiers: Overview, Bagging |
Overview by
Dietterich,Empirical
study by Opitz and Maclin Slides: PS, PDF |
|||
| No lecture | PS,PDF |
|||
| Ensemble classifiers: Boosting | Tutorial by Freund and
Schapire Slides: PS, PDF Applet by Ran El-Yaniv, Applet by Yoav Freund | |||
| First in-class examination | ||||
| Support Vector Machines | Burges tutorial Scholkopf tutorial |
|||
| Support Vector Machines - II | Slides: PS, PDF, |
|
||
| Reinforcement Learning - I | Barto & Sutton, Chapter 1, 3, 4 Slides: PS, PDF |
PS,PDF |
||
| Reinforcement Learning - II | Barto & Sutton, Sections 5.1-5.3, 6.1-6.3 Slides: Dynamic programming and Monte Carlo (PS,PDF), TD learning |
|||
| Reinforcement learning - III | Barto & Sutton,Sections 6.4-6.5, 7.1-7.4, 8.1-8.3 Slides: Monte Carlo vs. TD learning, Action values, Eligibility traces and function approximation (PS, PDF) |
PS,PDF |
||
| Unsupervised Learning: K-means clustering | Duda, Hart and Stork, Pattern classification, Chapter 10 Slides: PS, PDF |
|||
| Unsupervised Learning: Gaussian Mixture Models | Mitchell, Section 6.12. |
|||
| No lecture | |
|
||
| Machine learning: Present and future Class Evaluations |
|
|||
| Second in-class examination |