Salvato in:
Dettagli Bibliografici
Autori principali: Bittar, Alexandre, Garner, Philip N.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2404.14024
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929514214326272
author Bittar, Alexandre
Garner, Philip N.
author_facet Bittar, Alexandre
Garner, Philip N.
contents Understanding cognitive processes in the brain demands sophisticated models capable of replicating neural dynamics at large scales. We present a physiologically inspired speech recognition architecture, compatible and scalable with deep learning frameworks, and demonstrate that end-to-end gradient descent training leads to the emergence of neural oscillations in the central spiking neural network. Significant cross-frequency couplings, indicative of these oscillations, are measured within and across network layers during speech processing, whereas no such interactions are observed when handling background noise inputs. Furthermore, our findings highlight the crucial inhibitory role of feedback mechanisms, such as spike frequency adaptation and recurrent connections, in regulating and synchronising neural activity to improve recognition performance. Overall, on top of developing our understanding of synchronisation phenomena notably observed in the human auditory pathway, our architecture exhibits dynamic and efficient information processing, with relevance to neuromorphic technology.
format Preprint
id arxiv_https___arxiv_org_abs_2404_14024
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring neural oscillations during speech perception via surrogate gradient spiking neural networks
Bittar, Alexandre
Garner, Philip N.
Computation and Language
Neurons and Cognition
Understanding cognitive processes in the brain demands sophisticated models capable of replicating neural dynamics at large scales. We present a physiologically inspired speech recognition architecture, compatible and scalable with deep learning frameworks, and demonstrate that end-to-end gradient descent training leads to the emergence of neural oscillations in the central spiking neural network. Significant cross-frequency couplings, indicative of these oscillations, are measured within and across network layers during speech processing, whereas no such interactions are observed when handling background noise inputs. Furthermore, our findings highlight the crucial inhibitory role of feedback mechanisms, such as spike frequency adaptation and recurrent connections, in regulating and synchronising neural activity to improve recognition performance. Overall, on top of developing our understanding of synchronisation phenomena notably observed in the human auditory pathway, our architecture exhibits dynamic and efficient information processing, with relevance to neuromorphic technology.
title Exploring neural oscillations during speech perception via surrogate gradient spiking neural networks
topic Computation and Language
Neurons and Cognition
url https://arxiv.org/abs/2404.14024