manel.ayadi [at] dauphine.eu
PhD in Computer Science at LAMSADE – Paris-Dauphine
How does changing the voting system and the electoral district boundaries impact the outcome of the French legislative elections?
The aim of the project is to study the impact of changing the voting system (mixed electoral system, proportional representation …) and the electoral district boundaries on the outcome of the French legislative elections of 2017.
chloe.barre [at] pasteur.fr
PhD, LPTMC (Laboratoire de Physique Théorique de la Matière Condensée), Sorbonne University, Paris
Bayesian induction of the behavior of the larva.
decisions is a fundamental feature of animal behavior. Nevertheless, there
remains a large knowledge gap in linking neural architecture and behavioral
response. To bridge this gap, targeting individual neurons and having a simple
read-out of their activity is crucial, and Drosophila larvae are ideal
organisms for such an approach. My work is part of a larger project to explore
the relationship between neural network dynamics and decision making in
Drosophila larvae. I use Bayesian induction techniques and physical modeling to
understand this relationship.
combining video measurement experiments of larval behavior with advances in
modern optogenetics that allow the activation/inactivation of individual
neurons, a database of millions of larvae responding to the activation of
single neurons has been constructed. Although a machine learning approach that
projects larval videos into complex behavioral dictionaries has been developed,
some images remain ambiguous and the corresponding behavior is therefore poorly
detected. To improve behavior detection we describe the shape of the larva
using insights from solids mechanics. Using this physical model, we perform a
Bayesian induction to find parameters that describe the behavior of the larvae
in a more robust way.
Once the behaviors are properly detected and quantified, we want to detect all possible responses and modulations induced by the activation or inactivation of a neuron. We have written a simplified model that describes the dynamics and sequences of behaviors. With Bayesian inference I learn the parameters of my model and with a generative model and theses parameters I can recreate virtual larvae. These virtual larvae made it possible to separate neural responses between those provoking simple and immediate actions from those generating complex behaviors. It is thus possible to group neurons in terms of response.
By combining the techniques of biologists with probabilistic analysis techniques (including Bayesian inference), we can identify behavioral changes due to the activation/inactivation of neurons and thus will allow us to infer causal relationships between neural activity and behavioral patterns, and uncover how behavior emerges from activity in the connectome.
pierreablin [at] gmail.com
Understanding neural networks with differential equations.
Neural networks have encountered great empirical success, yet the reasons behind this success are still mostly unknown. It has recently been proposed to draw bridges between neural networks and differential equations. I study the nature of this link, and its implications on the theoretical and practical properties of neural networks.
ikko.yamane [at] dauphine.psl.eu
Ph.D. from The University of Tokyo
Counter factual inference with weakly supervised learning
In counter factual inference, one tries to predict what would happen if attributes of data were some values different from that actually observed. Existing counter factual inference methods often require expensive, controlled experiments to be conducted to collect necessary data. My research interest focuses on developing methods that only need cheaper and efficient experiments possibly with missing observations or milder conditions.
olga.seminck [at] cri-paris.org
Bachelor Vrije Universiteit (Amsterdam)
Master Université Paris Diderot, Doctorate Sorbonne Paris Cité
Computational Linguistics & Digital Humanities
My research project focuses on using techniques from the domain of Natural Language Processing to answer questions about language and style on big corpora of literary texts. Currently, I am working on a project about the notion of idiolect. I try to answer the questions 1) How does the idiolect of an author evolve over their lifetime ? and 2) Can we distinguish idiosyncratic changes from general diachronic language evolution?
Université Paris Dauphine-PSL
thomas.pontoizeau [at] lamsade.dauphine.fr
PhD in Computer Science at LAMSADE – Paris-Dauphine
Solving graph problems with machine learning and Monte-Carlo methods.
The aim of the project is to study graphs (combinatorial problems solving, structural aspects prediction) with tools from neural networks and Monte-Carlo methods.
franco.pellegr [at] gmail.com
PhD in Condensed Matter physics from SISSA, Trieste, Italy
Theory of neural network learning dynamics.
We want to describe the general mechanism that makes neural networks so effective in solving real life problems. We aim to use methods from statistical physics to build a model describing the dynamics of neural network parameters during training. We hope this insight will allow us to develop new training algorithms leading to improved networks.
misaki.ozawa2045 [at] gmail.com
PhD University of Tsukuba
Multiscale physics and wavelet transform.
In physics, multiscale phenomena are captured by the renormalization group. Wavelet transform is useful in analyzing multiscale behaviors. We investigate the relation between the renormalization group and the wavelet transform. Then we wish to obtain insight into how features are extracted hierarchically in neural networks.
Tanguy.marchand [at] ens.fr
Master from Ecole Polytechnique
Master from University of Cambridge
PhD from Sorbonne Université
Simulating physical stochastic processes using Machine Learning.
Physical stochastic processes such as turbulence, astrophysical maps and so on provide a wide range of non-Gaussian processes. My research is to develop new Machine Learning tools to better analyze and reproduce them.
georgialoukatou [at] gmail.com
PhD, École Normale Supérieure
Diversity and learnability in early language acquisition.
My research addresses issues of language learnability in cross-linguistic and cross-cultural settings. I follow an interdisciplinary approach, implementing computational modelling, corpus analysis and experimental methods.