Course information

Statistical learning is about the construction and study of systems that can automatically learn from data. With the emergence of massive datasets commonly encountered today, the need for powerful machine learning is of acute importance. Examples of successful applications include effective web search, anti-spam software, computer vision, robotics, practical speech recognition, and a deeper understanding of the human genome. This course gives an introduction to this exciting field, with a strong focus on kernels methods as a versatile tool to represent data, and recent convolutional and recurrent neural network models for visual recognition and sequence modeling.

Evaluation

  • homeworks (60%) + project (40%)

Course outline

Introduction

  • Motivating example applications
  • Linear classification models

Deep learning models

  • Convolutional neural networks
  • Recurrent neural networks
  • Unsupervised deep learning

Kernel Methods

  • Theory of RKHS and kernels
  • Supervised learning with kernels
  • Unsupervised learning with kernels
  • Kernels for structured data
  • Kernels for generative models

Calendar

Date Time Lecturer Room Topic
28/11/2019 9:45 - 12:45 XA E012 slides
5/12/2019 9:45 - 12:45 XA E012 slides
12/12/2018 9:45 - 12:45 XA E012 slides
19/12/2018 9:45 - 12:45 JM E012 slides 1-69
09/1/2019 9:45 - 12:45 JM E012
16/1/2019 9:45- 11:15 JM E012

Homeworks

There will be two homeworks given during the course. They count for 60% of the grade. It can be done by groups of 2 students, (but you cannot work twice with the same student), and should be sent by e-mail (a Pdf file in LateX with the given template) to julien.mairal@m4x.org. A Latex template is available here.
The first homework is available here and is due on January 10th.
The second homework is available here and is due on February 16th.

Projects

The project consists of experimenting with a learning approach of your choice to solve a given prediction problem. A small (2-page max) written report has to be submitted to describe what you did, and results obtained. Code should also be submitted, as well as results. The project counts for 40% of your grade. More information will be given during the class.
Data challenge is online! Follow the link given during the class to access the challenge on Kaggle

Reading material

Machine Learning and Statistics

  • Vapnik, The nature of statistical learning theory. Springer
  • Hastie, Tibshirani, Friedman, The elements of statistical learning. (free online)
  • J Shawe-Taylor, N Cristianini. Kernel methods for pattern analysis. 2004.

Jobs / Internships Opportunities

We have different intern/PhD opportunities in machine learning, image processing, bioinformatics and computer vision. It is best to discuss that matter early with us since the number of places is limited.