1 code implementation • Artificial Neural Networks and Machine Learning – ICANN 2012 • Simon Brodeur, Jean Rouat
This is due to the extremely non-linear dynamics of recurrent spiking neural networks.
no code implementations • 1 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.
no code implementations • 29 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.
no code implementations • 27 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.
1 code implementation • 26 Nov 2018 • Jerome Abdelnour, Giampiero Salvi, Jean Rouat
We introduce the task of acoustic question answering (AQA) in the area of acoustic reasoning.
no code implementations • 28 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.
no code implementations • 5 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.
no code implementations • 30 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.
1 code implementation • 11 Sep 2020 • Ismael Balafrej, Jean Rouat
Backpropagation algorithms on recurrent artificial neural networks require an unfolding of accumulated states over time.
no code implementations • 2 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.
no code implementations • 1 Jan 2021 • Luca Celotti, Simon Brodeur, Jean Rouat
Then, we benchmark on a real dataset of human dialogues.
1 code implementation • 9 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.
no code implementations • 11 Jun 2021 • Jerome Abdelnour, Jean Rouat, Giampiero Salvi
We also test the addition of a MALiMo module in our model on both CLEAR2 and DAQA.
1 code implementation • 12 Jun 2021 • Mathilde Brousmiche, Jean Rouat, Stéphane Dupont
Event classification is inherently sequential and multimodal.
1 code implementation • 29 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.
no code implementations • 1 Feb 2022 • Luca Herranz-Celotti, Jean Rouat
We show how it can be used to reduce the need of extensive grid-search of dampening, sharpness and tail-fatness of the SG.
no code implementations • 21 Mar 2022 • Nikhil Garg, Ismael Balafrej, Terrence C. Stewart, Jean Michel Portal, Marc Bocquet, Damien Querlioz, Dominique Drouin, Jean Rouat, Yann Beilliard, Fabien Alibart
To validate the system-level performance of VDSP, we train a single-layer spiking neural network (SNN) for the recognition of handwritten digits.
no code implementations • 14 Jul 2022 • Sidi Yaya Arnaud Yarga, Jean Rouat, Sean U. N. Wood
Finally, we show that several encoding methods result in improved performance over the conventional deep learning baseline in certain cases, further demonstrating the power of spike encoding algorithms in the encoding of real-valued signals and that neuromorphic implementation has the potential to outperform state of the art techniques.
no code implementations • 2 Aug 2023 • Emmanuel Calvet, Jean Rouat, Bertrand Reulet
Reservoir computing provides a time and cost-efficient alternative to traditional learning methods. Critical regimes, known as the "edge of chaos," have been found to optimize computational performance in binary neural networks.
no code implementations • 23 Aug 2023 • Luca Herranz-Celotti, Jean Rouat
However, analysing deep recurrent networks, we identify a new additive source of exponential explosion that emerges from counting gradient paths in a rectangular grid in depth and time.
no code implementations • 29 Oct 2023 • Ismael Balafrej, Fabien Alibart, Jean Rouat
Recurrent spiking neural networks (RSNNs) are notoriously difficult to train because of the vanishing gradient problem that is enhanced by the binary nature of the spikes.