Function approximation with uncertainty propagation in a VLSI spiking neural network

Corneil D, Sonnleithner D, Neftci E, Chicca E, Cook M, Indiveri G, Douglas R (2012)
Presented at the International Joint Conference on Neural Networks (IJCNN), Brisbane, Australia.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
OA
Autor*in
Corneil, D.; Sonnleithner, D.; Neftci, E.; Chicca, ElisabettaUniBi ; Cook, M.; Indiveri, G.; Douglas, R.
Abstract / Bemerkung
The brain combines and integrates multiple cues to take coherent, context-dependent action using distributed, event-based computational primitives. Computational models that use these principles in software simulations of recurrently coupled spiking neural networks have been demonstrated in the past, but their implementation in hybrid analog/ digital Very Large Scale Integration (VLSI) spiking neural networks remains challenging. Here, we demonstrate a distributed spiking neural network architecture comprising multiple neuromorphic VLSI chips able to reproduce these types of cue combination and integration operations. This is achieved by encoding cues as population activities of input nodes in a network of recurrently coupled VLSI Integrate-and-Fire (I&F) neurons. The value of the cue is place-encoded, while its uncertainty is represented by the width of the population activity profile. Relationships among different cues are specified through bidirectional connectivity matrices, shared between the individual input node populations and an intermediate node population. The resulting network dynamics bidirectionally relate not only the values of three variables according to a specified relation, but also their uncertainties. When cues on two populations are specified, the standard deviation of the activity in the unspecified population varies approximately linearly with the widths of the two input cues, and has less than 6% error in position compared to the value specified by the inputs. The results suggest a mechanism for recurrently relating cues such that missing information can both be recovered and assigned a level of certainty.
Erscheinungsjahr
2012
Seite(n)
2990-2996
Konferenz
International Joint Conference on Neural Networks (IJCNN)
Konferenzort
Brisbane, Australia
Konferenzdatum
2012-06-10 – 2012-06-15
Page URI
https://pub.uni-bielefeld.de/record/2473502

Zitieren

Corneil D, Sonnleithner D, Neftci E, et al. Function approximation with uncertainty propagation in a VLSI spiking neural network. Presented at the International Joint Conference on Neural Networks (IJCNN), Brisbane, Australia.
Corneil, D., Sonnleithner, D., Neftci, E., Chicca, E., Cook, M., Indiveri, G., & Douglas, R. (2012). Function approximation with uncertainty propagation in a VLSI spiking neural network. Presented at the International Joint Conference on Neural Networks (IJCNN), Brisbane, Australia. doi:10.1109/ijcnn.2012.6252780
Corneil, D., Sonnleithner, D., Neftci, E., Chicca, E., Cook, M., Indiveri, G., and Douglas, R. (2012).“Function approximation with uncertainty propagation in a VLSI spiking neural network”. Presented at the International Joint Conference on Neural Networks (IJCNN), Brisbane, Australia.
Corneil, D., et al., 2012. Function approximation with uncertainty propagation in a VLSI spiking neural network. Presented at the International Joint Conference on Neural Networks (IJCNN), Brisbane, Australia.
D. Corneil, et al., “Function approximation with uncertainty propagation in a VLSI spiking neural network”, Presented at the International Joint Conference on Neural Networks (IJCNN), Brisbane, Australia, 2012.
Corneil, D., Sonnleithner, D., Neftci, E., Chicca, E., Cook, M., Indiveri, G., Douglas, R.: Function approximation with uncertainty propagation in a VLSI spiking neural network. Presented at the International Joint Conference on Neural Networks (IJCNN), Brisbane, Australia (2012).
Corneil, D., Sonnleithner, D., Neftci, E., Chicca, Elisabetta, Cook, M., Indiveri, G., and Douglas, R. “Function approximation with uncertainty propagation in a VLSI spiking neural network”. Presented at the International Joint Conference on Neural Networks (IJCNN), Brisbane, Australia, 2012.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
Dieses Objekt ist durch das Urheberrecht und/oder verwandte Schutzrechte geschützt. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-09-06T09:18:00Z
MD5 Prüfsumme
7194448d20c9fa904fcaef0c154c7683

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar