Search Results for author: Sean U. N. Wood

Found 4 papers, 2 papers with code

Accelerating SNN Training with Stochastic Parallelizable Spiking Neurons

1 code implementation22 Jun 2023 Sidi Yaya Arnaud Yarga, Sean U. N. Wood

In this paper, we propose the Stochastic Parallelizable Spiking Neuron (SPSN) to overcome the sequential training limitation of LIF neurons.

Hardware-aware Training Techniques for Improving Robustness of Ex-Situ Neural Network Transfer onto Passive TiO2 ReRAM Crossbars

no code implementations29 May 2023 Philippe Drolet, Raphaël Dawant, Victor Yon, Pierre-Antoine Mouny, Matthieu Valdenaire, Javier Arias Zapata, Pierre Gliech, Sean U. N. Wood, Serge Ecoffey, Fabien Alibart, Yann Beilliard, Dominique Drouin

Passive resistive random access memory (ReRAM) crossbar arrays, a promising emerging technology used for analog matrix-vector multiplications, are far superior to their active (1T1R) counterparts in terms of the integration density.

Efficient spike encoding algorithms for neuromorphic speech recognition

no code implementations14 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.

speech-recognition Speech Recognition

Robust learning from corrupted EEG with dynamic spatial filtering

1 code implementation27 May 2021 Hubert Banville, Sean U. N. Wood, Chris Aimone, Denis-Alexander Engemann, Alexandre Gramfort

Building machine learning models using EEG recorded outside of the laboratory setting requires methods robust to noisy data and randomly missing channels.

BIG-bench Machine Learning EEG +1

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