Introduction to machine learning - Ecole Normale Superieure

Introduction to Machine Learning (2022 - 2023)

Summary

Statistical machine learning is a growing discipline at the intersection of computer science and applied mathematics (probability / statistics, optimization, etc.) and which increasingly plays an important role in technological innovation.

Unlike a course on traditional statistics, statistical machine learning is particularly focused on the analysis of data in high dimension, as well as the efficiency of algorithms to process the large amount of data encountered in multiple application areas such as image or sound analysis, natural language processing, bioinformatics or finance.

The objective of this class is to present the main theories and algorithms in statistical machine learning. The methods covered will rely amongst others on convex analysis arguments. The practical sessions (more than half of which will be realized with computers) will lead to simple implementations of the algorithms seen in class and with applications to various domains such as computer vision or natural language processing.

Prerequisite: probability theory (notion of random variables, convergence of random variables, conditional expectation), coding skills in python.

General information

This class is part of the Computer science courses taught at ENS in L3 in Spring 2023.

Teachers: Alessandro Rudi and Umut Simsekli.
Practical sessions: Bertille Follain.

The class will last 52 hours (30 hours of class + 22 hours of practical sessions) and can be validated for 9 ECTS.
Final grade: approximately 50% final exam, 50% homework.

Previous years: Spring 2022, Spring 2021, Spring 2020, Spring 2019, Fall 2018, 2017, 2016, 2015, 2014, 2013, 2012

Schedule and lecture notes

Thursday mornings from 8h30 to 12h15, room Emmy Noether. Typical session will be a lecture from 8h30 to 10h20, followed by a 20min break and the practical work (PW) from 10h40 to 12h15. Lecture notes and solutions to practical work and exercises will be updated here on the fly.

#	Date	Teacher	Title
1	09/02/2023	U. Simsekli	Introduction
2	16/02/2023	Alessandro Rudi Bertille Follain	Supervised learning and linear regression TD1 (Data: classificationA_train, classificationA_test, classificationB_train, classificationB_test, classificationC_train, classificationC_test, mnist_digits.mat, solution, NEW: all in one zip: ALL)
3	23/02/2023	Alessandro Rudi Bertille Follain	Logistic regression and convex analysis TD3,
	03/03/2023		No Class
4	09/03/2023	Alessandro Rudi Bertille Follain	Convex optimization TD4, TD4-english-version, solution to theoretical questions, solution to practical questions
5	16/03/2023	Alessandro Rudi Bertille Follain	Kernels Exercise sheet, solution
6	23/03/2023	Alessandro Rudi Bertille Follain	Learning with Kernels Numerical tour of Ridge and Lasso by Gabriel Peyre
7	30/03/2023	Alessandro Rudi Bertille Follain	Elements of Statistical Machine Learning Numerical tour of logistic classification by Gabriel Peyre , solution and slight nodification , data for first part
8	06/04/2023	Umut Simsekli Bertille Follain	Model Based ML - Maximum Likelihood TD on sgd , data , solution to the TD on SGD ,
9	13/04/2023	Umut Simsekli Bertille Follain	Unsupervised Learning TD on KNN , Small recap on KNN , data , TD on PCA , solution to the TD on KNN
10	20/04/2023	Umut Simsekli Bertille Follain	MCMC Sampling, lecture notes TD on MCMC , Solution to the TD on MCMC
	27/04/2023		No Class
	04/05/2023		No Class
11	11/05/2023	Umut Simsekli Bertille Follain	Neural Networks TD on Neural Networks
12	18/05/2023	No Class
	25/05/2022		No Class
13	01/06/2022	Umut Simsekli	Exam 8h30 to 12h30, the room H. Cartan. You can bring your notes.