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

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.


Editor(s):
Kaynak, Okyay
Alpaydin, Ethem
Oja, Erkki
Xu, Lei
Published in:
Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003, 839-845
Presented at:
13. ICANN / 10. ICONIP 2003, Istanbul, Turkey, June 26-29, 2003
Year:
2003
Publisher:
Springer
ISBN:
978-3-540-40408-8
Other identifiers:
Laboratories:




 Record created 2007-11-26, last modified 2018-01-28

External links:
Download fulltextURL
Download fulltextn/a
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)