Introduction to Machine Learning (NYU Paris, Fall 2018)

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)

Assignments policy

Except if explicitely stated otherwise, assignments are due at the beginning of each class.

 

The lecture notes will be available here soon:  ML2018 Lecture notes

Practice (theory) Questions for each exam can be found by clicking on those exams below

Exam : 60% of the grade (30% midterm, 30% final)

The Midterm exam will take place on Thursday october 25th, 3pm during class

Assignments : 30 % of the grade (Tentative schedule below)

 Final Project : 10 % of the grade (Tentative schedule below)

 

The Github page for the class will be hosted at https://acosse.github.io/IntroMLFall2018/ and will be used for the lab and the assignments. You can also click on each “Lab” in the schedule below and this will re-direct you to the github page.

Tentative schedule:

Legend: Lab sessions are in green, Homeworks due dates are in red (right side of the table), dates related to the project are in orange.

Week # date Topic Assignements
Week 1 09/04, 09/06 General Intro + reminders on proba and inference. Part I, Part II  
    Part I : supervised Learning  
Week 2 09/11, 09/13 Linear and logistic regression, regularization and Compressed sensing
Linear Classification Part I, Part II, Note on the Bias-Variance trade-off		 HW1
Week 3 09/18, 09/20 Lab 1: Intro to Python + linear class. and regression  
Week 4 09/25, 09/27 Non Linear classification, Kernel methods, SVM, Parts I & 2  HW2
Week 5 10/2, 10/4 Neural Networks, Optimization, Stochastic Optimization, Deep learning, Part I HW1 due
Week 6 10/9, 10/11 Lab 2: Non Linear regression and classification, Neural Nets  
    Part II : Unsupervised Learning  
Week 7 10/16, 10/18 Clustering, Linear Latent variable models  Slides HW2 due, HW3
Week 8 10/23, 10/25 Linear Latent variable models (Part II), PCA, ICA, GMM, EM algorithm,
Non linear LVM,  Part I, Part II		 Project choice 
Week 9 10/30, 11/1 Non Linear LVM  and Manifold Learning  Parts 1&2  
Week 10 11/6, 11/8 Lab 3: Unsupervised Learning HW3 due
Week 11 11/13, 11/15 Generalization, complexity and VC Theory  
Week 12 11/20, 11/22 Probabilistic models, HMM, Bayesian Nets + Advanced topics,
Reinforcement Learning, Adversarial Learning, Part I		 HW 4
Week 13 11/27, 11/29 Lab 4: Exam review, wrap up Project due date
Week 14 12/4, 12/6 Final Exam  

 

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.

    1. Start by downloading anaconda: https://www.anaconda.com/download/#macos 

 

    1. If you don’t have a text editor yet, you can download sublime text (see interesting keyboard shortcuts here)

 

  1. We will use multiple libraries during the class. Among the important ones, you can find the documentation from scikit-learn, numPy, Pandas

Data sets can be downloaded on the following websites: