Introduction to Machine Learning (NYU Paris, Spring 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, 9.00am – 10.15am (Paris Time), Room 410
Recitations: Thursday 10.30am – 12.00pm (Paris time). Room 410
Office hour: Tuesday 10.30am – 12.00pm (Paris time)
Except if explicitely stated otherwise, assignments are due at the beginning of each class.
Practice (theory) Questions for each exam can be found by clicking on those exams below
Assignments : 30 % of the grade (Tentative schedule below)
The Github page for the class will be hosted at https://github.com/acosse/MachineLearningSpring2021 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
Legend: Lab sessions are in green, Homeworks are in red (right side of the table), dates related to the project are in orange.
|Week 1||01/26, 01/28||General Intro + reminders on proba and inference.
|Part I : supervised Learning|
|Week 2||02/02, 02/04||Linear and logistic regression, regularization and Compressed sensing
Linear Classification Part I, Part II, Note on the Bias-Variance trade-off
Demo Gradient Descent, Additional Note Ridge vs LASSO
|Week 3||02/09, 02/11||
Linear and logistic regression, Linear Classification (Part II)
Demo 2, Demo 3, Demo Logistic vs OLS: demo1, demo2
|Week 4||02/16, 02/18||Non Linear classification, Kernel methods, SVM, Parts I & 2
Assign. 2, Assig. 1 due
|Week 5||02/23, 02/25||Neural Networks, Optimization, Stochastic Optimization, Deep learning, Part I
Lab 4 (Part I) / Solutions
|Week 6||03/02, 03/04||Lab 2: Non Linear regression and classification, Neural Nets
Lab 5 Zoom Slides
| Assign. 2 due,
|Part II : Unsupervised Learning|
|Week 7||03/09, 03/11||Clustering, Linear Latent variable models Slides
|Week 8||03/16, 03/18||Linear Latent variable models (Part II), PCA, ICA, GMM, EM algorithm,
Non linear LVM, Part I Part II, Additional Note on MVN
|Week 9||03/23, 03/25||Non Linear LVM and Manifold Learning Parts 1&2
|Week 10||03/30, 04/01||Lab 3: Unsupervised Learning||Readings
|Week 11||04/06, 04/08||Generalization, complexity and VC Theory|
|Week 12||04/13, 04/15||Probabilistic models, HMM, Bayesian Nets||
|Week 13||04/20, 04/22||Advanced topics,
Reinforcement Learning, Adversarial Learning, Part I
|Week 14||04/27, 04/29||Revisions|
|Week 15||05/04, 05/06||Project Presentations|
- The elements of Statistical Learning, Hastie, Tibshirani, Friedman
- Pattern Recognition and Machine Learning, Bishop
- Machine Learning, a probabilistic perspective, Murphy
- Non linear dimensionality reduction, Lee, Verleysen.
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.
- Start by downloading anaconda: https://www.anaconda.com/download/#macos
- If you don’t have a text editor yet, you can download sublime text (see interesting keyboard shortcuts here)
Data sets can be downloaded on the following websites: