Teaching

I’m teaching on a regularly basis on various topics (scientific computing, machine learning, computational neuroscience, computer science). Some courses have taken place at the national level and consequently they’re in French. Some others have been taught at the international level and they’re in English. Sources for the slides are available upon request (by mail).

Computational Neuroscience

From single neuron to behavior (2016)

This lecture introducing computational neuroscience was given during the VIII course of the International School of Bioelectromagnetics “Alessandro Chiabrera”: Electromagnetic Fields and the Nervous System: Biological Effects, Biophysical Mechanisms, Methods, and Medical Applications, 2016, Erice, Italy.

→ Slides (PDF, 28Mo)

Advanced neural fields (2015)

This lecture on advanced neural fields and cognition was given during the “Neural mass and neural field models” tutorial session of the Computational Neuroscience Symposium (CNS), 2015, Prague, Czech Republic.

→ Slides (PDF, 28Mo)

Scientific visualization

Matplotlib tutorial (2015)

Matplotlib is probably the single most used Python package for 2D-graphics. It provides both a very quick way to visualize data from Python and to output publication-quality figures in many formats. This tutorial proposes to cover the main aspects of matplotlib through a serie of exercises.

→ Website
→ GitHub sources

10 Simple rules for better figures (2014)

Scientific visualization is classically defined as the process of graphically displaying scientific data. However, this process is far from direct or automatic. There are so many different ways to represent the same data: scatter plots, linear plots, bar plots, and pie charts, to name just a few. Furthermore, the same data, using the same type of plot, may be perceived very differently depending on who is looking at the figure. A more accurate definition for scientific visualization would be a graphical interface between people and data.

→ Website
→ GitHub sources

Numerical computing

From Python to Numpy (2017)

There is already a fair number of book about Numpy (see Bibliography) and a legitimate question is to wonder if another book is really necessary. As you may have guessed by reading these lines, my personal answer is yes, mostly because I think there’s room for a different approach concentrating on the migration from Python to Numpy through vectorization. There is a lot of techniques that you don’t find in books and such techniques are mostly learned through experience. The goal of this book is to explain some of them and to make you acquire experience in the process.

→ Website
→ GitHub sources

100 Numpy exercises (2016)

This lesson gather 100 Numpy exercises ranging from the very easy to the extreme esoteric ones (not for the faint of heart). Those exercises have been collected on the numpy mailing lists, on stack overflow and from other sources as well (personal communication mostly). The goal is both to offer a quick reference for new and old users and to provide also a set of exercices for those who teach.

→ Website
→ GitHub sources

Introduction to Numpy (2015)

NumPy is the fundamental package for scientific computing with Python. Besides its obvious scientific uses, NumPy can also be used as an efficient multi-dimensional container of generic data. Arbitrary data-types can be defined and this allows NumPy to seamlessly and speedily integrate with a wide variety of projects. This lesson is based on the programming of the game of life using numpy for efficient computation.

→ Website
→ GitHub sources

Machine learning

Reinforcement learning (2014)

This lecture on reinforcement learning was given at the Third Latin American Summer School in Computational Neuroscience, Valparaiso (Chile) in January

  1. It introduces Markov decision processes (MDP) and Reinforcement Learning (RL).

→ Slides (MDP) (PDF, 1.1Mo)
→ Slides (RL) (PDF, 0.9Mo)

Artificial Neural Networks (2014)

These lecture introduces learning, memory and artificial neural networks (perceptron, multi-layer perceptron and self-organising maps) for master students (in French).

→ Slides (Introduction) (PDF, 6.5Mo)
→ Slides (Perceptrons) (PDF, 2.0Mo)
→ Slides (Self-organising maps) (PDF, 2.5Mo)

Computer science

Cyber-Criminalité, contes et légendes du cyberspace (2012, French)

Depuis les heures glorieuses du phreaking où des adolescents cherchaient simplement à téléphoner gratuitement (1960), jusqu’à la mise au point par des états de virus informatiques pour des attaques ciblées (2010), le visage de la cybercriminalité s’est radicalement transformé en l’espace de quelques années. Là où l’on trouvait des passionés d’informatique, on trouve aujourd’hui des états, des industries, des mafias et des script kiddies. Les possibilités de piratage et de fraude se sont par ailleurs multipliées depuis la généralisation de l’accès à internet et de la téléphonie mobile. Sachant que le point d’entrée privilégié dans un système est l’utilisateur lambda, il est plus que jamais nécessaire de rester vigilant.

→ Slides (PDF, 3.1Mo)

C++ Crash Course (2009)

This is an introduction to C++ for C programmers. If you can’t understand the code below, you’d better start with a C tutorial:

#include <stdio.h>
void main (int argc, char **argv)
{
    printf( "Hello World!\n" );
}

Else, you can proceed to the website.

→ Website

Visual Attention

This series of talks was given at the National Institute of Informatics (NII) in Tokyo during my stay in Japan in 2010. This was done in the context of the NII International advanced lectures series on ICT.

Embodied Cognition (2010)

Twenty years ago, R. Brooks revealed to the A.I. community that elephants don’t play chess. Ten years later, A. Clark explained that “we ignore the fact that the biological mind is, first and foremost, an organ for controlling the biological body. Minds make motions, and they must make them fast - before the predator catches you, or before your prey gets away from you. Minds are not disembodied logical reasoning devices”. This lecture proposes to look back at (almost) 60 years of Artificial Intelligence researches in order to address the question of what has been accomplished so far towards our understanding of intelligence and cognition. In this context, we’ll introduce the action-perception loop, the embodied cognition paradigm and the symbol grounding problem as it has been identified by Steve Harnad. This problem has became prominent in the cognitive science society and the idea that a symbol is much more than a mere meaningless token that can be processed through some algorithm sheds a new light on higher brain functions. More specifically, we’ll explain how those theories can impact modeling on computer vision.

→ Slides (PDF, 3.4Mo)

Visual attention (2010)

This lecture proposes to review current psychological and physiological data as and classical experiments related to visual attention as well as anatomical and physiological data related to the oculomotor control in the primate. We will introduce the two main forms of visual attention, namely exogeneous (bottom up) and endogeneous (top down) visual attention that are known to play a critical role in the perception and processing of a visual scene. Facilitating and inhibitory effects of visual attention will be presented in light of Posner experiments (1980) related to the concept of inhibition of return that play a major role in a number of computational models of visual attention. Finally, integrative theories related to visual attention will be introduced, namely the premotor theory of attention, the active perception paradigm and the deictic codes for the embodiment of cognition.

→ Slides (PDF, 2.1Mo)

Introduction to Neural Fields (2010)

This lecture introduces main concepts related to classical artificial neural networks as well as computational neuroscience. Standard artificial neural network models related to supervised, unsupervised and reinforcment learning will be briefly introduced as well as key concepts from neuro-anatomy and neuro-physiology. This lecture will also focus on the dynamic neural field (DNF) Theory as it has been originally introduced by Wilson and Cowan in the early seventies and later formalized by S.I. Amari and J.G. Taylor. These theories explain the dynamic of pattern formation for lateral-inhibition type homogeneous neural fields with general connections. They show that, in some conditions, continuous attractor neural networks are able to maintain a localised bubble of activity in direct relation with the excitation provided by a stimulation. We will investigate further these theories in order to explain how their functional properties can be linked to visual attention defined as the capacity to attend to one stimulus in spite of noise, distractors or saliency effects.

→ Slides (PDF, 2.6Mo)

Models of Visual Attention (2010)

The visual exploration of a scene involves the interplay of several competing processes (for example to select the next saccade or to keep fixation) and the integration of bottom-up (e.g. contrast) and top-down information (the target of a visual search task). Identifying the neural mechanisms involved in these processes and the integration of these information remain a challenging question. Visual attention refers to all these processes, both when the eyes remain fixed (covert attention) and when they are moving (overt attention). Popular computation models of visual attention consider that the visual information remains fixed when attention is deployed while the primate are executing around three saccadic eye movements per second, abruplty changing the whole visual information. We’ll introduce in this lecture a model relying on dynamic neural fields and show that covert and overt attention can emerge from such a substratum. We’ll identify and propose a possible interaction of four elementary mechanisms for selecting the next locus of attention, memorizing the previously attended locations, anticipating the consequences of eye movements and integrating bottom-up and top-down information in order to perform a visual search task with saccadic eye movements.

→ Slides (PDF, 4.8Mo)