Skip to main content

Lectures

# DATE TOPIC NOTES
1 Aug 26 Introduction Overview of topics and applications (none)
2 Aug 31 Supervised Learning Linear Regression: gradient descent, Normal equations. PDF
3 Sep 2 Supervised Learning Probabilistic Interpretation, Logistic Regression PDF
4 Sep 7 Supervised Learning Newton's method, Locally weighted Linear Regression, Nearest Neighbors (previous pdf)
5 Sep 9 Supervised Learning Exponential Families, Generalized Linear Models (previous pdf),
Optional: Paper
6 Sep 14 Optimization Convex functions, Convex problems pdf (pages 1-24),
pdf (pages 1-23)
7 Sep 16 Supervised Learning Generative Learning Algorithms, Gaussian Discriminant Analysis PDF
8 Sep 21 Supervised Learning Generative (contd.), Model and feature selection Feature selection
9 Sep 23 Supervised Learning Kernels Parts of Bishop, ch 6.
Parts of Notes
10 Sep 28 Supervised Learning SVM. Duality (pages 1-6, 8-13)
11 Sep 30 Unsupervised Learning Curse of Dimensionality, Dimensionality Reduction, PCA Bishop, ch 12. (or PCA notes)
12 Oct 14 Adaboost Object Detection PPTX
13 Oct 19 Unsupervised Learning Mixture of Gaussians, EM PDF
14 Oct 21 Unsupervised Learning examples of EM, clustering, spectral clustering PDF, k-means notes.
Spectral.
-- Oct 22, 2-4pm Mid-term Project presentation Details
15 Oct 26 Unsupervised Learning Multi-dimensional Scaling (MDS), Isomaps Isomap paper
15 Oct 28 Review Independent Component Analysis (ICA), Learning Review PDF
-- Oct 28 Mid-term Exam, 7:30-10pm Supervised+Unsupervised Learning+Optimization+Theory THR 203
18 Nov 2 Unsupervised Learning Non Negative Matrix Factorization Bishop, ch 12. (Partial/complementary material covered here.)
Full details in Prob PCA paper.
NNMF Paper
17 Nov 4
19 Nov 9 Probabilistic Graphical Models Introduction, Representation, Markov Blanket, variable elimination Bishop, ch 8.
Others (not necessarily relating directly to the lecture notes): html, pdf
20 Nov 11 Probabilistic Graphical Models HMM, Inference on a chain (sum-product specific case) Bishop, ch 8.
21 Nov 16 Probabilistic Graphical Models Kalman Filters Bishop, ch 8. slides
22 Nov 18 Probabilistic Graphical Models Directed / Undirected graphs, MRFs Bishop, ch 8.
23 Nov 23 Probabilistic Graphical Models Sum-product, Max-product Bishop, ch 8.
24 Nov 23 Probabilistic Graphical Models Examples. MRF: discrete (image-denoising), continuous (depth estimation), sampling/particle filters Optional reading: Paper, Paper
25 Nov 30 Paper reading Graphical Models Paper 1, Paper 2
25 Dec 2 Special Topic Deep Learning Paper 1, Paper 2
- Dec 1-10 Peer Review Period Review 2 other reports
- Dec 17, Friday 2-5pm Projects