ELL409

ELL409: Machine Intelligence and Learning

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

Instructor: Sumeet Agarwal
4 credits (3-0-2)
Overlaps with: ELL784, COL774, COL341
I Semester 2019–20
M Tu F 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% (Better Minor 20%, Worse Minor 10%) [Paper I + Answers; Working] [Paper II + Answers]
[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] [Quiz]

Audit criteria

Grade B- or better, plus 75% attendance

References

Christopher M. Bishop, Pattern Recognition and Machine Learning (PRML). Springer, 2006.
Peter Flach, Machine Learning: The Art and Science of Algorithms that Make Sense of Data. Cambridge University Press, 2012.
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, 2016. [Free online]
Michael Nielsen, Neural Networks and Deep Learning. Determination Press, 2015. [Free online]
Stuart J. Russell and Peter Norvig, Artificial Intelligence: A Modern Approach. Pearson, 3rd Edition, 2010.

Planned outline

Serial no.	Topics	Lecture nos.	PRML Chapters	Other References	Slides
1	Introduction: Nature of Intelligence and Learning; Revision of Probability Theory, Distributions, Bayesian Inference	1–7	1, 2	Review of Probability Theory; The Multivariate Gaussian Distribution
2	Basics of Learning: Tasks, Models, Features	7		Flach Chapter 1	Very quick introduction
3	Supervised Learning: Linear Regression Models	8–15	1, 3	Regression notes	PRML Chapter 1; 'Beauty' in Scientific Theories; PRML Chapter 3
4	Supervised Learning: Classification, Decision Trees and Rule-Based Models	15–17		Flach Chapters 2, 5, 6	Flach Chapter 6
5	Supervised Learning: The Perceptron and Logistic Regression	18–20	4		Linear models for classification
6	Supervised Learning: Kernels, Support Vector Machines	21–26	6, 7	SVM notes; SVM tutorial; Properties of kernels; Platt's SMO paper; SVM demo
7	Supervised Learning: Neural Networks, Deep Learning	27–32	5	ANN tutorial; Geoff Hinton lecture on deep learning; Convolutional neural nets: tutorial, demos; Sparse autoencoder notes; Baby Human video clip on face recognition; Backpropagation with max pooling notes	Google's unsupervised deep learning
8	Unsupervised Learning: Clustering, Mixture Models, Latent Variables, Expectation-Maximisation	33–36	9	K-means notes; GMM notes; EM notes	Clustering
9	Unsupervised Learning: Dimensionality Reduction, Factor/Component Analysis	37–39	12	PCA notes; PCA tutorial	PCA
10	Supervised Feature Selection	40		Flach Chapter 10
11	Reinforcement Learning	41–42		Russell & Norvig Chapter 22
12	Conclusions and Philosophical Issues	42

[Teaching home]