Search Results for author: Jean Rouat

Found 17 papers, 6 papers with code

Voltage-Dependent Synaptic Plasticity (VDSP): Unsupervised probabilistic Hebbian plasticity rule based on neurons membrane potential

no code implementations21 Mar 2022 Nikhil Garg, Ismael Balafrej, Terrence C. Stewart, Jean Michel Portal, Marc Bocquet, Damien Querlioz, Dominique Drouin, Jean Rouat, Yann Beilliard, Fabien Alibart

This update is dependent on the membrane potential of the presynaptic neuron, which is readily available as part of neuron implementation and hence does not require additional memory for storage.

Surrogate Gradients Design

no code implementations1 Feb 2022 Luca Herranz-Celotti, Jean Rouat

Evidence supports that training can be robust to the choice of SG shape, after an extensive search of hyper-parameters.

Adaptive Approach For Sparse Representations Using The Locally Competitive Algorithm For Audio

1 code implementation29 Sep 2021 Soufiyan Bahadi, Jean Rouat, Éric Plourde

An oriented grid search optimization was applied to adapt the gammachirp's parameters and improve the Matching Pursuit (MP) algorithm's sparsity along with the reconstruction quality.

Signals to Spikes for Neuromorphic Regulated Reservoir Computing and EMG Hand Gesture Recognition

1 code implementation9 Jun 2021 Nikhil Garg, Ismael Balafrej, Yann Beilliard, Dominique Drouin, Fabien Alibart, Jean Rouat

Using a simple machine learning algorithm after spike encoding, we report performance higher than the state-of-the-art spiking neural networks on two open-source datasets for hand gesture recognition.

EMG Gesture Recognition Hand Gesture Recognition +1

AVECL-UMONS database for audio-visual event classification and localization

no code implementations2 Oct 2020 Mathilde Brousmiche, Stéphane Dupont, Jean Rouat

We introduce the AVECL-UMons dataset for audio-visual event classification and localization in the context of office environments.

General Classification

P-CRITICAL: A Reservoir Autoregulation Plasticity Rule for Neuromorphic Hardware

1 code implementation11 Sep 2020 Ismael Balafrej, Jean Rouat

Backpropagation algorithms on recurrent artificial neural networks require an unfolding of accumulated states over time.

AriEL: volume coding for sentence generation

no code implementations30 Mar 2020 Luca Celotti, Simon Brodeur, Jean Rouat

This partially supports to the hypothesis that encoding information into volumes instead of into points, can lead to improved retrieval of learned information with random sampling.

Language coverage and generalization in RNN-based continuous sentence embeddings for interacting agents

no code implementations5 Nov 2019 Luca Celotti, Simon Brodeur, Jean Rouat

While it is known that those embeddings are able to learn some structures of language (e. g. grammar) in a purely data-driven manner, there is very little work on the objective evaluation of their ability to cover the whole language space and to generalize to sentences outside the language bias of the training data.

Dialogue Generation Sentence Embeddings

From Visual to Acoustic Question Answering

no code implementations28 Feb 2019 Jerome Abdelnour, Giampiero Salvi, Jean Rouat

The AQA task consists of analyzing an acoustic scene composed by a combination of elementary sounds and answering questions that relate the position and properties of these sounds.

Acoustic Question Answering Question Answering +1

Classification of auditory stimuli from EEG signals with a regulated recurrent neural network reservoir

no code implementations27 Apr 2018 Marc-Antoine Moinnereau, Thomas Brienne, Simon Brodeur, Jean Rouat, Kevin Whittingstall, Eric Plourde

The use of electroencephalogram (EEG) as the main input signal in brain-machine interfaces has been widely proposed due to the non-invasive nature of the EEG.

EEG General Classification

HoME: a Household Multimodal Environment

no code implementations29 Nov 2017 Simon Brodeur, Ethan Perez, Ankesh Anand, Florian Golemo, Luca Celotti, Florian Strub, Jean Rouat, Hugo Larochelle, Aaron Courville

We introduce HoME: a Household Multimodal Environment for artificial agents to learn from vision, audio, semantics, physics, and interaction with objects and other agents, all within a realistic context.

OpenAI Gym reinforcement-learning

Moving Toward High Precision Dynamical Modelling in Hidden Markov Models

no code implementations1 Jul 2016 Sébastien Gagnon, Jean Rouat

In this paper, we propose that finely-tuned HMM topologies are essential for precise temporal modelling and that this approach should be investigated in state-of-the-art HMM system.

Speech Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.