A robust sound perception model suitable for neuromorphic implementation

Coath M, Sheik S, Chicca E, Indiveri G, Denham S, Wennekers T (2014)
Neuromorphic Engineering 7(278): 1-10.

Zeitschriftenaufsatz | Veröffentlicht | Englisch
 
Download
OA
Autor/in
; ; ; ; ;
Abstract / Bemerkung
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.
Stichworte
neuromorphic; VLSI; information; plasticity; modeling; auditory
Erscheinungsjahr
2014
Zeitschriftentitel
Neuromorphic Engineering
Band
7
Ausgabe
278
Seite(n)
1-10
ISSN
1662-453X
eISSN
1662-453X
Page URI
https://pub.uni-bielefeld.de/record/2654984

Zitieren

Coath M, Sheik S, Chicca E, Indiveri G, Denham S, Wennekers T. A robust sound perception model suitable for neuromorphic implementation. Neuromorphic Engineering. 2014;7(278):1-10.
Coath, M., Sheik, S., Chicca, E., Indiveri, G., Denham, S., & Wennekers, T. (2014). A robust sound perception model suitable for neuromorphic implementation. Neuromorphic Engineering, 7(278), 1-10. doi:10.3389/fnins.2013.00278
Coath, M., Sheik, S., Chicca, E., Indiveri, G., Denham, S., and Wennekers, T. (2014). A robust sound perception model suitable for neuromorphic implementation. Neuromorphic Engineering 7, 1-10.
Coath, M., et al., 2014. A robust sound perception model suitable for neuromorphic implementation. Neuromorphic Engineering, 7(278), p 1-10.
M. Coath, et al., “A robust sound perception model suitable for neuromorphic implementation”, Neuromorphic Engineering, vol. 7, 2014, pp. 1-10.
Coath, M., Sheik, S., Chicca, E., Indiveri, G., Denham, S., Wennekers, T.: A robust sound perception model suitable for neuromorphic implementation. Neuromorphic Engineering. 7, 1-10 (2014).
Coath, M., Sheik, S., Chicca, Elisabetta, Indiveri, G., Denham, S., and Wennekers, T. “A robust sound perception model suitable for neuromorphic implementation”. Neuromorphic Engineering 7.278 (2014): 1-10.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-09-06T09:18:21Z
MD5 Prüfsumme
4881fc9ca298029177c7947f6bc81c57

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®

Quellen

PMID: 24478621
PubMed | Europe PMC

Suchen in

Google Scholar