François Fleuret

Short Biography

François Fleuret is the head of the Machine Learning group at the IDIAP Research Institute, Switzerland, since 2007, and adjunct faculty at the École Polytechnique Fédérale de Lausanne (EPFL) since 2011, where he teaches machine learning. He has published more than 80 papers in peer-reviewed international conferences and journals. He was awarded a PhD in Mathematics from INRIA and the University of Paris VI in 2000, and a Habilitation degree in Mathematics from the University of Paris XIII in 2006. His main research interest is machine learning, with a particular focus on computational aspects and small sample learning, and applications in computer vision. He is the Associate Editor of the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) since 2012, served as Area Chair for NIPS (2012, 2014, 2016, 2017) and ICCV (2012) and on the program committees of many top-tier international conferences in machine learning and computer vision.

Course "Artificial Intelligence"

Date

October 19th, 2018

Description

This course will focus on machine learning. It will start with an introduction covering why to use learning, going from artificial neural networks to ‘deep learning’, why it works now, learning from data, capacity and bias-variance, and standard clustering and embedding. Then, the following topics will be covered:

• Tensor operations - what a tensor is, linear regression, manipulating high-dimension signals and using GPUs.
• Multi-layer perceptrons, back-propagation, autograd - a bit of history, limitation of linear classifiers, multi-layer perceptrons, training and gradient descent, back-propagation, and autograd.
• Convolutional neural networks - convolutions, poolings, image classification, and standard convnets.
• Going deeper - stochastic gradient descent, full example, dropout, batch normalization, and residual networks.
• Generative models - visualizing the processing, adversarial examples, autoencoders, and generative Adversarial Networks