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).

Instructors: Sumeet Agarwal, Jayadeva
4 credits (3-0-2)
Overlaps with: ELL784, COL774, COL341
I Semester 2021–22
M Tu F 12–12:50, Microsoft Teams

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

Evaluation components

Assignments/Minors/Quizzes: 60% (there will be a variety of evaluations of these types through the semester of different weightages; at the end the best subset worth 60 marks will be considered for the overall grade.) [Assignment 1] [Minor; Solutions] [Assignment 2] [Assignment 3]
Major: 40%

Audit criteria

30% for audit pass as per Institute rules; however, some of the evaluation components will be different for auditors. It is suggested that you make up your mind early on whether you wish to audit the course, as this will also reduce the time/effort you need to put into the evaluations. So auditing is recommended for all those who either feel they will not be able to put too much time into the course, or those who may not fully have the expected mathematical background.

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	Exercises
1	Introduction: Nature of Intelligence and Learning; Revision of Probability Theory, Distributions, Bayesian Inference	1–8	1, 2	Review of Probability Theory; The Multivariate Gaussian Distribution		Problem Set 1 [Data: P3.mat] [Solutions] Problem Set 2 [Solutions]
2	Basics of Learning: Tasks, Models, Features	8–9		Flach Chapter 1	Very quick introduction
3	Supervised Learning: Linear Regression Models	10–17	1, 3	Regression notes	PRML Chapter 1; 'Beauty' in Scientific Theories; PRML Chapter 3
4	Supervised Learning: Linear Classifiers, the Perceptron and Logistic Regression	18–21	4		Linear models for classification
5	Supervised Learning: Neural Networks, Deep Learning	22–23; 27–28	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
6	Supervised Learning: Kernels, Support Vector Machines	23–26	6, 7	SVM notes; SVM tutorial; Properties of kernels; Platt's SMO paper; SVM demo
7	Learning Theory	29–32
8	Unsupervised Learning: Dimensionality Reduction, Factor/Component Analysis	33–34	12	PCA notes; PCA tutorial	PCA

[Teaching home]