ML Group Mines ParisTech 2016-17 Fontainebleau, France

  1. Home
  2. ML Group

Week 1 - Introduction - R. Alais

Slides: "Introduction au Machine Learning"

Additional content:

  • Chapter 1 of Murphy's book.

  • A Few Useful Things to Know about Machine Learning., P. Domingos, 2012

  • Practical advice for applying Machine Learning (adapted from Andrew Ng lectures)

    • Week 2 - Decision Trees and Random Forests - S. Drouyer

    Coming soon.

    Week 3 - Neural Networks - A. Fehri

    Slides : "Réseaux de neurones artificiels" - Related code here

    Additional content:

  • Practical recommendations for gradient-based training of deep architectures , Y. Bengio, 2012

  • Representation Learning: A Review and New Perspectives, Y. Bengio, 2012

  • Deep Learning in Neural Networks: An Overview , J. Schmidhuber, 2014

  • A Neural Network Playground

  • Neural Network Course at USherbrooke

    • Week 4 - SVM and Kernel Methods - M. Demangeot

    Slides : "Support Vector Machines" - Related code here

    Additional content:

  • Lecture notes on SVM , Andrew Ng

  • Tutorials on SVMs and Kernels

    • Week 5 - Jobs in ML

    Slides :

  • Mind map on jobs in ML (note: install mindmapmaker on drive for it to work), S. Drouyer
  • "Data scientist and Machine Learning engineers : who’s who?", M. Pereira
  • "ML and computer science", P. Guillou

    • Additional content:

  • Where machines could replace humans — and where they can’t (yet), Michael Chui, James Manyika, and Mehdi Miremadi

    • Week 6 - PCA and Kernel PCA - K. Chang

    Slides : "PCA and Kernel PCA"

    Additional content:

  • Lecture: PCA and MDS., Varun Kanade

  • Lecture: kernel PCA. Unsupervised learning 2011., Rita Osadchy

  • Implementing a Principal Component Analysis, S. Raschka

  • Kernel tricks and nonlinear dimensionality reduction via RBF kernel PCA, S. Raschka

  • Sections 12.1 and 12.3 of Bishop's textbook

    • Week 7 - Expectation Maximization - J-B. Gasnier

    Slides : "Expectation Maximization"

    Additional content:

  • L'algorithme EM : une courte présentation., F. Santos

  • Lecture: Expectation Maximization: Algorithm and Applications., E. Weinstein

  • Lecture: Méthodes de classification pour la segmentation d’image, F. Chamroukhi

    • Week 8 - Convolutional Neural Networks - R. Alais

    Slides : "Convolutional Neural Networks"

    Additional content:

  • Hands-on TensorBoard (TensorFlow Dev Summit 2017)

  • CS231n: Convolutional Neural Networks for Visual Recognition, Stanford CS class notes

  • Intro to Deep Learning (Udacity Nanodegree), Siraj Raval

    • Week 9 - Some Uses of Graphs in Machine Learning - M. Pereira

    Slides : "Some Uses of Graphs in Machine Learning" - Related code here (in R)

    Additional content:

  • Graphs in Machine Learning, Lectures 0 - 4, Michal Valko

  • Semi-Supervised Learning Using Gaussian Fields and Harmonic Functions, Zhu et al.

  • On Spectral Clustering: Analysis and algorithm, Ng et al.

    • Week 10 - Fantastic Architectures and How to Use Them - P. Guillou

    Slides : "Fantastic Architectures and How to Use Them" - Related code here

    Additional content:

    Coming soon.