Cargando…
A robust sound perception model suitable for neuromorphic implementation
We have recently demonstrated the emergence of dynamic feature sensitivity through exposure to formative stimuli in a real-time neuromorphic system implementing a hybrid analog/digital network of spiking neurons. This network, inspired by models of auditory processing in mammals, includes several mu...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2014
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3894459/ https://www.ncbi.nlm.nih.gov/pubmed/24478621 http://dx.doi.org/10.3389/fnins.2013.00278 |
_version_ | 1782299857257496576 |
---|---|
author | Coath, Martin Sheik, Sadique Chicca, Elisabetta Indiveri, Giacomo Denham, Susan L. Wennekers, Thomas |
author_facet | Coath, Martin Sheik, Sadique Chicca, Elisabetta Indiveri, Giacomo Denham, Susan L. Wennekers, Thomas |
author_sort | Coath, Martin |
collection | PubMed |
description | We have recently demonstrated the emergence of dynamic feature sensitivity through exposure to formative stimuli in a real-time neuromorphic system implementing a hybrid analog/digital network of spiking neurons. This network, inspired by models of auditory processing in mammals, includes several mutually connected layers with distance-dependent transmission delays and learning in the form of spike timing dependent plasticity, which effects stimulus-driven changes in the network connectivity. Here we present results that demonstrate that the network is robust to a range of variations in the stimulus pattern, such as are found in naturalistic stimuli and neural responses. This robustness is a property critical to the development of realistic, electronic neuromorphic systems. We analyze the variability of the response of the network to “noisy” stimuli which allows us to characterize the acuity in information-theoretic terms. This provides an objective basis for the quantitative comparison of networks, their connectivity patterns, and learning strategies, which can inform future design decisions. We also show, using stimuli derived from speech samples, that the principles are robust to other challenges, such as variable presentation rate, that would have to be met by systems deployed in the real world. Finally we demonstrate the potential applicability of the approach to real sounds. |
format | Online Article Text |
id | pubmed-3894459 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2014 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-38944592014-01-29 A robust sound perception model suitable for neuromorphic implementation Coath, Martin Sheik, Sadique Chicca, Elisabetta Indiveri, Giacomo Denham, Susan L. Wennekers, Thomas Front Neurosci Neuroscience We have recently demonstrated the emergence of dynamic feature sensitivity through exposure to formative stimuli in a real-time neuromorphic system implementing a hybrid analog/digital network of spiking neurons. This network, inspired by models of auditory processing in mammals, includes several mutually connected layers with distance-dependent transmission delays and learning in the form of spike timing dependent plasticity, which effects stimulus-driven changes in the network connectivity. Here we present results that demonstrate that the network is robust to a range of variations in the stimulus pattern, such as are found in naturalistic stimuli and neural responses. This robustness is a property critical to the development of realistic, electronic neuromorphic systems. We analyze the variability of the response of the network to “noisy” stimuli which allows us to characterize the acuity in information-theoretic terms. This provides an objective basis for the quantitative comparison of networks, their connectivity patterns, and learning strategies, which can inform future design decisions. We also show, using stimuli derived from speech samples, that the principles are robust to other challenges, such as variable presentation rate, that would have to be met by systems deployed in the real world. Finally we demonstrate the potential applicability of the approach to real sounds. Frontiers Media S.A. 2014-01-17 /pmc/articles/PMC3894459/ /pubmed/24478621 http://dx.doi.org/10.3389/fnins.2013.00278 Text en Copyright © 2014 Coath, Sheik, Chicca, Indiveri, Denham and Wennekers. http://creativecommons.org/licenses/by/3.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Neuroscience Coath, Martin Sheik, Sadique Chicca, Elisabetta Indiveri, Giacomo Denham, Susan L. Wennekers, Thomas A robust sound perception model suitable for neuromorphic implementation |
title | A robust sound perception model suitable for neuromorphic implementation |
title_full | A robust sound perception model suitable for neuromorphic implementation |
title_fullStr | A robust sound perception model suitable for neuromorphic implementation |
title_full_unstemmed | A robust sound perception model suitable for neuromorphic implementation |
title_short | A robust sound perception model suitable for neuromorphic implementation |
title_sort | robust sound perception model suitable for neuromorphic implementation |
topic | Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3894459/ https://www.ncbi.nlm.nih.gov/pubmed/24478621 http://dx.doi.org/10.3389/fnins.2013.00278 |
work_keys_str_mv | AT coathmartin arobustsoundperceptionmodelsuitableforneuromorphicimplementation AT sheiksadique arobustsoundperceptionmodelsuitableforneuromorphicimplementation AT chiccaelisabetta arobustsoundperceptionmodelsuitableforneuromorphicimplementation AT indiverigiacomo arobustsoundperceptionmodelsuitableforneuromorphicimplementation AT denhamsusanl arobustsoundperceptionmodelsuitableforneuromorphicimplementation AT wennekersthomas arobustsoundperceptionmodelsuitableforneuromorphicimplementation AT coathmartin robustsoundperceptionmodelsuitableforneuromorphicimplementation AT sheiksadique robustsoundperceptionmodelsuitableforneuromorphicimplementation AT chiccaelisabetta robustsoundperceptionmodelsuitableforneuromorphicimplementation AT indiverigiacomo robustsoundperceptionmodelsuitableforneuromorphicimplementation AT denhamsusanl robustsoundperceptionmodelsuitableforneuromorphicimplementation AT wennekersthomas robustsoundperceptionmodelsuitableforneuromorphicimplementation |