CSC 311
Lecture Slides and Recommended Readings
(courtesy of Rich Zemel, Raquel Urtasun, Sanja Fidler,
Emad Andrews,
Amir-massoud Farahmand and others)
Lecture 1:
Introduction and Nearest Neighbours
(ESL 1, 2.1-2.3, 2.5.)
Lecture 2:
Linear Regression
(ESL 2.9, 3.2. PRML 1.0-1.1, 1.2.5, 3.1)
Contour maps
Lecture 3:
Linear Classification: Logistic Regression
(ESL 4.1, 4.2, 4.4)
Lecture 4:
Multi-class Classification and Neural Nets
(
Notes
, ESL 11.3, 11.4, PRML 5.0, 5.1, 5.2.0, 5.2.4, 5.3.0, 5.3.1, 5.3.2)
Lecture 5:
Probabilistic Models
(ESL 6.6.3, PRML 1.2.0, 1.2.3, 2.1, 4.2.3)
Lecture 6:
Probabilistic Models (continued)
(ESL 4.3.0, PRML 1.2.4, 4.2)
Lecture 7:
Clustering: K-means and EM
Lecture 8:
Reinforcement Learning
Lecture 9:
Ensemble Methods
(PRML 14.2-14.3)
Lecture 10:
Dimensionality Reduction: PCA and Autoencoders
Lecture 11:
Convolutional Neural Networks
Lecture 12:
Decision Trees