ELL784/EEL709

ELL784: Introduction to Machine Learning

EEL709: Pattern Recognition

If you're doing the course, please join the Piazza forum (the access code has been announced in class).

Instructor: Sumeet Agarwal
3 credits (3-0-0)
Pre-requisite: MTL106/MAL250
Overlaps with: ELL409, COL774/CSL341, MAL803
II Semester 2015–16
M W 11–11:50, Th 12–12:50, LH 310

[Machine Learning: A very quick introduction.]
[Introduction to a similar course, written by Amos Storkey at the University of Edinburgh.]

Evaluation components

Minors: 30% [Paper I + Solutions] [Paper II; Solutions] [Re-Minor] (Better Minor 20%, Worse Minor 10%)
[Re-Minor policy: Only one re-Minor will be conducted towards the end of the semester. The syllabus will be everything covered up until the date of Minor II. Only those with a valid medical certificate covering the date of one of the original Minors will be admitted to the re-Minor.]
Major: 24% [Paper]
Class attendance/participation: 10%
Assignments: 36% (Demos 24%, Quiz (to be held alongside Major) 12%) [1] [2] [3] [4] [Quiz]

References

Christopher M. Bishop, Pattern Recognition and Machine Learning (PRML). Springer, 2006.
David J. C. MacKay, Information Theory, Inference, and Learning Algorithms. Cambridge University Press, 2003. [Free online, and apparently better than Harry Potter, unless one speaks Welsh or Latin.]
Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning. MIT Press, in preparation. [Free online]
Michael Nielsen, Neural Networks and Deep Learning. Determination Press, 2015. [Free online]

Planned outline

Serial no.	Topics	Lecture nos.	PRML Chapters	Other References	Slides
1	Introduction, Revision of Probability Theory and Distributions	1–8	1, 2	Review of Probability Theory; The Multivariate Gaussian Distribution	Very quick introduction; PRML Chapter 1
2	Supervised Learning: Linear Regression Models	9–10	3	Regression notes	PRML Chapter 3
3	Supervised Learning: Classification, Linear Discriminant Analysis	11–12	4	Generative learning notes	Linear models for classification
4	Supervised Learning: Kernels, Support Vector Machines	13–15; 24–25	6, 7	SVM notes; SVM tutorial; Properties of kernels; Platt's SMO paper; SVM demo
5	Unsupervised Learning: Clustering, Mixture Models, Expectation-Maximisation, Eigenanalysis	16–23	9, 12	K-means notes; GMM notes; EM notes; PCA notes; PCA tutorial	Clustering
6	Supervised Learning: Neural Networks, Deep Learning	26–32	5	ANN tutorial; Geoff Hinton lecture on deep learning; Convolutional neural nets: tutorial, demos; Sparse autoencoder notes; AlphaGo paper	Google's unsupervised deep learning
7	Feature Selection	33
8	Naïve Bayes, Probabilistic Graphical Models	34–37	8	Naïve Bayes notes; Bayesian Networks notes	Graphical Models
9	Unsupervised Learning: Latent Variables, Factor/Component Analysis	38–40	12	Factor analysis notes	PCA
10	Hidden Markov Models	41–42	13	HMM notes; Microsoft's photo-real talking head [demo paper]

[Teaching home]