Machine Learning textbook

slides (original) (raw)

Machine Learning, Tom Mitchell, McGraw-Hill.

Slides for instructors:

The following slides are made available for instructors teaching from the textbook Machine Learning, Tom Mitchell, McGraw-Hill.

Slides are available in both postscript, and in latex source. If you take the latex, be sure to also take the accomanying style files, postscript figures, etc.

• Ch 1. Introduction. (postscript 3.8Meg), (gzipped postscript 317k) (pdf) (latex source )
• Ch 2. Concept Learning. (postscript 347k), (gzipped postscript 100k) (pdf) (latex source )
• Ch 3. Decision Tree Learning. (postscript 530k), (gzipped postscript 143k) (pdf) (latex source )
• Ch 4. Artificial Neural Networks. (postscript 1.83Meg), (gzipped postscript 329k) (pdf) (latex source )
• Ch 5. Evaluating Hypotheses. (postscript 212k), (gzipped postscript 67k) (pdf) (latex source )
• Ch 6. Bayesian Learning. (postscript 261k), (gzipped postscript 81k) (pdf) (latex source )
  see also slides on learning Bayesian networks by Friedman and Goldszmidt.
• Ch 7. Computational Learning Theory. (postscript 160k), (gzipped postscript 50k) (pdf) (latex source )
• Ch 8. Instance Based Learning. (postscript 138k), (gzipped postscript 39k) (pdf) (latex source )
• Ch 9. Genetic Algorithms. (postscript 245k), (gzipped postscript 72k) (pdf) (latex source )
• Ch 10. Learning Sets of Rules. (postscript 185k), (gzipped postscript 57k) (pdf) (latex source )
• Ch 11. Analytical Learning. ( postscript 261k) (pdf) ( latex source)
• Ch 12. Combining Inductive and Analytical Learning. ( postscript 419k), (gzipped postscript 103k) (pdf) (latex source )
• Ch 13. Reinforcment Learning. (postscript 172k), (gzipped postscript 40k) (pdf) (latex source )

Additional homework and exam questions:

Check out the homework assignments and exam questions from the Fall 1998 CMU Machine Learning course (also includes pointers to earlier and later offerings of the course).

Additional tutorial materials:

Support Vector Machines:

• Tutorial information on Support vector machines
• Freeware implementation : SVM Light by Thorsten Joachims.
• K.-R. Müller, S. Mika, G. Rätsch, K. Tsuda, and B. Schölkopf.An introduction to kernel-based learning algorithms.IEEE Neural Networks, 12(2):181-201, May 2001. (PDF)