Mathieu Galtier

Mathieu Galtier
Rythm

Doctor

About

35
Publications
6,291
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,017
Citations
Additional affiliations
December 2013 - present
National Institute for Research in Computer Science and Control
Position
  • PostDoc Position

Publications

Publications (35)
Article
590 Background: Triple-Negative Breast Cancer (TNBC) is characterized by high metastatic potential and poor prognosis with limited treatment options. Neoadjuvant chemotherapy (NACT) is the standard of care in non-metastastic setting due to the ability to assess pathologic responses providing important prognostic information and guidance in adjuvant...
Article
Recent studies have shown that slow oscillations (SOs) can be driven by rhythmic auditory stimulation, which deepens slow‐wave sleep (SWS) and improves memory and the immune‐supportive hormonal milieu related to this sleep stage. While different attempts have been made to optimise the driving of the SOs by changing the number of click stimulations,...
Preprint
Full-text available
Pharmaceutical industry can better leverage its data assets to virtualize drug discovery through a collaborative machine learning platform. On the other hand, there are non-negligible risks stemming from the unintended leakage of participants' training data, hence, it is essential for such a platform to be secure and privacy-preserving. This paper...
Article
Introduction Le diagnostic de mélanome est l’un des points les plus cruciaux de la prise en charge dermatologique. Récemment, le développement d’algorithmes de deep learning pour le diagnostic de tumeurs cutanées malignes et en particulier de mélanome amorce une révolution dans le diagnostic par le dermatologue. Cependant, la plupart des algorithme...
Preprint
Full-text available
Triple-Negative Breast Cancer (TNBC) is a rare cancer, characterized by high metastatic potential and poor prognosis, and has limited treatment options compared to other breast cancers. The current standard of care in non-metastatic settings is neoadjuvant chemotherapy (NACT), with the goal of breast-conserving surgery and for an in vivo assessment...
Article
Full-text available
Data-driven machine learning (ML) has emerged as a promising approach for building accurate and robust statistical models from medical data, which is collected in huge volumes by modern healthcare systems. Existing medical data is not fully exploited by ML primarily because it sits in data silos and privacy concerns restrict access to this data. Ho...
Preprint
Data-driven Machine Learning has emerged as a promising approach for building accurate and robust statistical models from medical data, which is collected in huge volumes by modern healthcare systems. Existing medical data is not fully exploited by ML primarily because it sits in data silos and privacy concerns restrict access to this data. However...
Preprint
Full-text available
Machine learning is promising, but it often needs to process vast amounts of sensitive data which raises concerns about privacy. In this white-paper, we introduce Substra, a distributed framework for privacy-preserving, traceable and collaborative Machine Learning. Substra gathers data providers and algorithm designers into a network of nodes that...
Article
Full-text available
Many neurons possess dendrites enriched with sodium channels and are capable of generating action potentials. However, the role of dendritic sodium spikes remain unclear. Here, we study computational models of neurons to investigate the functional effects of dendritic spikes. In agreement with previous studies, we found that point neurons or neuron...
Preprint
Full-text available
In many neuron types, the dendrites contain a significant density of sodium channels and are capable of generating action potentials, but the significance and role of dendritic sodium spikes are unclear. Here, we use simplified computational models to investigate the functional effect of dendritic spikes. We found that one of the main features of n...
Article
Introduction Recent studies have shown that slow oscillations (SO) can be driven by auditory closed-loop stimulations to deepen slow wave sleep (SWS) and thereby improve memory and the immune-supportive hormonal milieu related to this sleep stage. While different attempts have been made to optimize the driving of the SO by changing the number of st...
Article
Full-text available
Recent research has shown that auditory closed-loop stimulation can enhance sleep slow oscillations (SO) to improve N3 sleep quality and cognition. Previous studies have been conducted in lab environments. The present study aimed to validate and assess the performance of a novel ambulatory wireless dry-EEG device (WDD), for auditory closed-loop sti...
Data
Individual polar plots. The targeted phase was 45° which represents the middle of the ascending slope. 90° corresponds to the peak of the up state, 270 degrees to the trough of the down state.
Data
Individual hypnograms scored by the sleep expert. Stimulation triggers are shown in red.
Data
Individual multitaper EEG spectrogram of a full sleep night from the WDD (Top) and on the PSG (Bottom) recordings.
Article
Objectif Le but de notre recherche est de construire un logiciel open-source permettant aux médecins, techniciens du sommeil et ingénieurs de visualiser et analyser des polysomnographies (PSG), mais aussi de fournir des outils d’intelligence artificielle (IA) pour accélérer et automatiser l’analyse tout en assurant la sécurité des données des enreg...
Article
Objectif La présente étude a pour objectif d’évaluer la performance d’un nouveau dispositif EEG ambulatoire, le bandeau Dreem First (WDD) dans le cadre d’un usage ambulatoire avec stimulations auditives en boucle fermée. Méthodes La performance du WDD pour détecter automatiquement le N3 et pour émettre des stimulations auditives sur les OL a été é...
Preprint
Full-text available
Objective Recent research has shown that auditory closed-loop stimulations can enhance sleep slow oscillations (SO) to improve N3 sleep quality and cognition. Previous studies have been conducted in a lab environment and on a small sample size. The present study aimed at validating and assessing the performance of a novel ambulatory wireless dry-EE...
Article
Full-text available
Sleep stage classification constitutes an important preliminary exam in the diagnosis of sleep disorders and is traditionally performed by a sleep expert who assigns to each 30s of signal a sleep stage, based on the visual inspection of signals such as electroencephalograms (EEG), electrooculograms (EOG), electrocardiograms (ECG) and electromyogram...
Article
Full-text available
Morpheo is a transparent and secure machine learning platform collecting and analysing large datasets. It aims at building state-of-the art prediction models in various fields where data are sensitive. Indeed, it offers strong privacy of data and algorithm, by preventing anyone to read the data, apart from the owner and the chosen algorithms. Compu...
Article
Full-text available
Extracting invariant features in an unsupervised manner is crucial to perform complex computation such as object recognition, analyzing music or understanding speech. While various algorithms have been proposed to perform such a task, Slow Feature Analysis (SFA) uses time as a means of detecting those invariants, extracting the slowly time-varying...
Article
Full-text available
In this work we study the dynamics of systems composed of numerous interacting elements interconnected through a random weighted directed graph, such as models of random neural networks. We develop an original theoretical approach based on a combination of a classical mean-field theory originally developed in the context of dynamical spin-glass mod...
Article
Full-text available
The architecture of a neural network controlling an unknown environment is presented. It is based on a randomly connected recurrent neural network from which both perception and action are simultaneously read and fed back. There are two concurrent learning rules implementing a sort of ideomotor control: (i) perception is learned along the principle...
Article
Echo State Networks are efficient time series predictors which highly depend on the value of the spectral radius of the reservoir connections. Based on recent results on the mean field theory of driven random recurrent neural networks, which allow the computation of the largest Lyapunov exponent of an ESN, we develop a cheap algorithm to establish...
Article
A method is provided for designing and training noise-driven recurrent neural networks as models of stochastic processes. The method unifies and generalizes two known separate modeling approaches, Echo State Networks (ESN) and Linear Inverse Modeling (LIM), under the common principle of relative entropy minimization. The power of the new method is...
Article
Full-text available
Identifying, formalizing, and combining biological mechanisms that implement known brain functions, such as prediction, is a main aspect of research in theoretical neuroscience. In this letter, the mechanisms of spike-timing-dependent plasticity and homeostatic plasticity, combined in an original mathematical formalism, are shown to shape recurrent...
Article
Full-text available
Deriving tractable reduced equations of biological neural networks capturing the macroscopic dynamics of sub-populations of neurons has been a longstanding problem in computational neuroscience. In this paper, we propose a reduction of large-scale multi-population stochastic networks based on the mean-field theory. We derive, for a wide class of sp...
Article
Full-text available
This paper deals with the application of temporal averaging methods to recurrent networks of noisy neurons undergoing a slow and unsupervised modification of their connectivity matrix called learning. Three time-scales arise for these models: (i) the fast neuronal dynamics (ii) the intermediate external input to the system and (iii) the slow learni...
Article
Full-text available
We show how a Hopfield network with modifiable recurrent connections undergoing slow Hebbian learning can extract the underlying geometry of an input space. First, we use a slow and fast analysis to derive an averaged system whose dynamics derives from an energy function and therefore always converges to equilibrium points. The equilibria reflect t...
Article
In this thesis, we propose to give a mathematical sense to the claim: the neocortex builds itself a model of its environment. We study the neocortex as a network of spiking neurons undergoing slow STDP learning. By considering that the number of neurons is close to infinity, we propose a new mean-field method to find the ''smoother'' equation descr...
Article
Based on the analysis of a certain class of linear operators on a Banach space, we provide a closed form expression for the solutions of certain linear partial differential equations with non-autonomous input, time delays and stochastic terms, which takes the form of an infinite series expansion.
Article
Full-text available
Les modèles de champs neuronaux sont des outils intéressants pour la modélisation, a l'échelle mésoscopique, des aires corticales du cerveau. Ils possèdent les caractéristiques mathématiques qui les rendent exploitables, a savoir l'existence, l'unicité et la stabilité (sous conditions) de leur solution. Ainsi nous décrivons un modèle de l'aire visu...
Article
We introduce a general learning principle designed to capture the dynamics of an input into a recurrent neural network. By minimizing the relative entropy between a given input dynamical system and the spontaneous activity of the neural network, we derive a new unsupervised learning rule. This learning rule can be interpreted in terms of biological...

Network

Cited By

Projects

Project (1)
Archived project
The goal of Dreemcare is to build an open collaborative platform collecting and analyzing various sleep data while guaranteeing privacy and ownership.