Introduction to Machine Learning (NYU Paris, Fall 2021)
Machine Learning is getting more and more important these days with applications ranging from autonomous driving to computer assisted medicine, including weather or financial forecasting. In this class we will study the mathematical foundations of the current machine learning algorithms.
We will cover the main models from both supervised learning including linear and non linear regression and classification (kernel methods, support vector machine, neural networks) and unsupervised learning (including clustering, gaussian mixtures, self organizing maps, principal and independent component analysis and non linear dimensionality reduction)
We will review basic concepts in probability and statistics. We will discuss Bayesian vs frequentist statistics and model/parameter inference, as well as sampling methods.
Finally, we will also discuss the important question of model assessment and selection.
The class will follow the structure
1. Lectures (introduction of the new material that will be needed during the lab sessions and for the assignements)
2. Programming (lab) sessions, (you have the opportunity to apply what you have learned during the lecture, and you can ask all the questions you want to make sure you understand everything before the assignement)
3. Assignments (You are given a new problem and you are evaluated on your ability to use the course material to solve this new problem)
Schedule and Classroom
Lecture: Tuesday/Thursday, 3.30pm – 4.45pm (Paris Time), Room 410
Recitations: Tuesday (C03) 5.00am – 6.25pm (Paris time) and
Thursday (C02) 5.00am – 6.25pm . Room 410
Office hour: Thursday 10.30am – 12.00pm (Paris time)
Assignments policy
Except if explicitely stated otherwise, assignments are due at the beginning of each class.
Current (temporary) version of the notes: Lecture notes as well as the list of sections for the Final
Practice (theory) Questions for each exam can be found by clicking on those exams below
Exam : 60% of the grade (30% Midterm (Material), 30% Final(Material))
Assignments : 30 % of the grade (Tentative schedule below)
Final Project : 10 % of the grade (Tentative schedule below, List of suggestions, Poster guidelines)
The Github page for the class will be hosted at https://github.com/acosse/IntroductiontoMLFall2021 and will be used for the lab and the assignments. You can also click on each “Lab” in the schedule below which will display a rendering of the notebooks through nbviewer. To access the file itself (and to be able to download it), you should go directly to github
Tentative schedule:
Legend: Lab sessions are in green, Homeworks are in red (right side of the table), dates related to the project are in orange.
Week #  date  Topic  Assignements 
Week 1  09/02  General Intro + reminders on proba and inference.
Part I, 
Readings 
Part I : supervised Learning  
Week 2  09/07, 09/09  Linear and logistic regression, regularization and Compressed sensing Linear Classification Part I, Part II, Note on the BiasVariance tradeoff Demo Gradient Descent, Additional Note Ridge vs LASSO Handwritten Notes : Intro + Gradient descent, Normal Eqts + regularization MLE + MAP, Bias Variance Tradeoff 
Readings Assignment 1 
Week 3  09/11, 09/16 
Linear and logistic regression, Linear Classification (Part II) Lab 2 Solutions, Demo 2, Demo 3, Demo Logistic vs OLS: demo1, demo2 Handwritten Notes : Intro class. + Logistic Regr., Perceptron 
Readings 
Week 4  09/21, 09/23  Non Linear classification, Kernel methods, SVM, Parts I & 2
Lab 3, Solutions, Handwritten Notes : Kernels, MaxMargin I, MaxMargin II 
Readings
Assign. 2, Assig. 1 due 
Week 5  09/28, 09/30  Neural Networks, Optimization, Stochastic Optimization, Deep learning, Part I
Lab 4 (Part I) / Solutions (Part I), Solutions (tmp, Part II) 
Readings 
Week 6  10/05, 10/07  Lab 2: Non Linear regression and classification, Neural Nets,
Handwritten notes backprop, Lab 5 Zoom Slides 
Assign. 2 due, Project choice MidTerm Revisions 
Part II : Unsupervised Learning  
Week 7  10/12, 10/14  Clustering, Linear Latent variable models Slides
Lab 6, (partial) Solutions 
Readings 
Week 8  10/19, 10/21  Linear Latent variable models (Part II), PCA, ICA, GMM, EM algorithm, Non linear LVM, Part I Part II, Additional Note on MVN Demos FA/PCA , Handwritten Notes LVM (Part I), Handwritten Notes LVM (Part II) Lab 7, (partial) Solutions 

Week 9  10/26, 10/28  Non Linear LVM and Manifold Learning Parts 1&2

Readings 
Week 10  11/02, 11/04  Lab 3: Unsupervised Learning  Readings Assign. 3 
Week 11  11/09, 11/11  Generalization, complexity and VC Theory  
Week 12  11/16, 11/18  Probabilistic models, HMM, Bayesian Nets  
Week 13  11/23, 11/25  Advanced topics, Reinforcement Learning, Adversarial Learning, Slides RL Lab RL 

Week 14  11/30, 12/02  Revisions  
Week 15  12/07, 12/09  Project Presentations  
Week 16  12/14, 12/16  Final Exams  
Week 17  12/21, 12/23  Final Exams 
Lab Sessions and programming policy
The lab sessions will require you to do some programming. It is strongly recommended to use python as it is more flexible and will be useful to you when moving to pytorch later on for more advanced machine learning methods requiring GPU processing.
Downloading and getting started with Python.
Data sets can be downloaded on the following websites: