Course Material
Lecture Slides
- 1. Intro to AI (loosely following chapt 1 & 2 from R&N)
- 2. Machine Learning Intro (Learning from observations - chapt 13 / 18; Bishop chapt 1)
- 2b. Bayesian Decision theory (Prof. K. Venkataramani) (based on ch. 1 & 2 of DHS)
- 2c. Neural networks, Deep learning, Kernel methods and SVM (bishop sections)
- 3. Robotics
- 3b. Robotics-RMP-exercise
- 4. Computer Vision
- 5. Logic quiz (w solution)
- 6. End-Sem Solutions
Other Readings
Christopher Bishop PRML 2010:
- Intro to Regression, Probability, Information theory (Chapter 1)
- k-NN (section 2.5)
- Kernel methods and SVMs (sections 6.1, 7.1, 7.2)
Duda, Hart and Stork, Pattern Reognition 2001
- Binary classification & Naive bayes (Chapter 1,2)