Contraction Properties of VLSI Cooperative Competitive Neural Networks of Spiking Neurons

Neftci E, Chicca E, Indiveri G, Slotine J-J, Douglas R (2008)
Presented at the Advances in Neural Information Processing Systems 20 (NIPS), Vancouver, British Columbia, Canada.

Download
OA
Conference Paper | Published | English
Author
; ; ; ;
Editor
Platt, J.C. ; Koller, D. ; Singer, Y. ; Roweis, S.
Abstract
A non–linear dynamic system is called contracting if initial conditions are forgotten exponentially fast, so that all trajectories converge to a single trajectory. We use contraction theory to derive an upper bound for the strength of recurrent connections that guarantees contraction for complex neural networks. Specifically, we apply this theory to a special class of recurrent networks, often called Cooperative Competitive Networks (CCNs), which are an abstract representation of the cooperative-competitive connectivity observed in cortex. This specific type of network is believed to play a major role in shaping cortical responses and selecting the relevant signal among distractors and noise. In this paper, we analyze contraction of combined CCNs of linear threshold units and verify the results of our analysis in a hybrid analog/digital VLSI CCN comprising spiking neurons and dynamic synapses.
Publishing Year
Conference
Advances in Neural Information Processing Systems 20 (NIPS)
Location
Vancouver, British Columbia, Canada
PUB-ID

Cite this

Neftci E, Chicca E, Indiveri G, Slotine J-J, Douglas R. Contraction Properties of VLSI Cooperative Competitive Neural Networks of Spiking Neurons. Presented at the Advances in Neural Information Processing Systems 20 (NIPS), Vancouver, British Columbia, Canada.
Neftci, E., Chicca, E., Indiveri, G., Slotine, J. - J., & Douglas, R. (2008). Contraction Properties of VLSI Cooperative Competitive Neural Networks of Spiking Neurons. Presented at the Advances in Neural Information Processing Systems 20 (NIPS), Vancouver, British Columbia, Canada.
Neftci, E., Chicca, E., Indiveri, G., Slotine, J. - J., and Douglas, R. (2008).“Contraction Properties of VLSI Cooperative Competitive Neural Networks of Spiking Neurons”. Presented at the Advances in Neural Information Processing Systems 20 (NIPS), Vancouver, British Columbia, Canada.
Neftci, E., et al., 2008. Contraction Properties of VLSI Cooperative Competitive Neural Networks of Spiking Neurons. Presented at the Advances in Neural Information Processing Systems 20 (NIPS), Vancouver, British Columbia, Canada.
E. Neftci, et al., “Contraction Properties of VLSI Cooperative Competitive Neural Networks of Spiking Neurons”, Presented at the Advances in Neural Information Processing Systems 20 (NIPS), Vancouver, British Columbia, Canada, Cambridge, MA: 2008.
Neftci, E., Chicca, E., Indiveri, G., Slotine, J.-J., Douglas, R.: Contraction Properties of VLSI Cooperative Competitive Neural Networks of Spiking Neurons. Presented at the Advances in Neural Information Processing Systems 20 (NIPS), Vancouver, British Columbia, Canada (2008).
Neftci, E., Chicca, Elisabetta, Indiveri, G., Slotine, J.-J., and Douglas, R. “Contraction Properties of VLSI Cooperative Competitive Neural Networks of Spiking Neurons”. Presented at the Advances in Neural Information Processing Systems 20 (NIPS), Vancouver, British Columbia, Canada, Cambridge, MA, 2008.
Main File(s)
Access Level
OA Open Access
Last Uploaded
2012-01-20 11:36:59

This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar