Proceedings chapter
OA Policy
English

Online processing of multiple inputs in a sparsely-connected recurrent neural network

Presented at

Istanbul (Turkey), June 26-29, 2003

Published in

Kaynak, O.; Alpaydin, E.; Oja, E.; Xu, L. (Ed.), Artificial Neural Networks and Neural Information Processing - ICANN/ICONIP, p. 839-845

Publisher

Berlin : Springer

Collection

  • Lecture Notes in Computer Science; 2714/2003

Publication date

2003

Abstract

The storage and short-term memory capacities of recurrent neural networks of spiking neurons are investigated. We demonstrate that it is possible to process online many superimposed streams of input. This is despite the fact that the stored information is spread throughout the network. We show that simple output structures are powerful enough to extract the diffuse information from the network. The dimensional blow up, which is crucial in kernel methods, is efficiently achieved by the dynamics of the network itself.

UNIGE affiliation entities

Not a UNIGE publication

Citation (ISO format)

MAYOR, Julien, GERSTNER, Wulfram. Online processing of multiple inputs in a sparsely-connected recurrent neural network. In: Artificial Neural Networks and Neural Information Processing - ICANN/ICONIP. Kaynak, O.; Alpaydin, E.; Oja, E.; Xu, L. (Ed.). Istanbul (Turkey). Berlin : Springer, 2003. p. 839–845. (Lecture Notes in Computer Science) doi: 10.1007/3-540-44989-2_100

Main files (1)

Proceedings chapter

Identifiers

ISBN

978-3-540-40408-8
605views
266downloads

Technical informations

Creation

29/08/2012 17:49:00

First validation

29/08/2012 17:49:00

Update

14/03/2023 17:39:58

Status update

14/03/2023 17:39:57

Last indexation

29/10/2024 20:30:56
All rights reserved by Archive ouverte UNIGE and the University of Geneva
OpenAIRE Indexed & Validated