NeuroCOLT

Neural Networks and Computational Learning Theory

 

About NeuroCOLT

Papers Archive

1994 1995
1996 1997
1998 1999
2000 2001

Books

info@neurocolt.org

NeuroCOLT Technical Report NC-TR-96-031

An Efficient Implementation of Sigmoidal Neural Nets in Temporal Coding with Noisy Spiking Neurons

Wolfgang Maass
Institute for Theoretical Computer Science
Technische Universitaet Graz
Austria

Abstract
We show that networks of rather realistic models for biological neurons can in principle simulate arbitrary feedforward sigmoidal neural nets in a way which has previously not been considered. This new approach is based on temporal coding by single spikes (respectively by the timing of synchronous firing in pools of neurons), rather than on the traditional interpretation of analog variables in terms of firing rates. The resulting new simulation is substantially faster and apparently more consistent with experimental results about fast information processing in cortical neural systems.  As a consequence we can show that networks of noisy spiking neurons are "universal approximators" in the sense that they can approximate with regard to temporal coding any given continuous function of several variables.  Our new proposal for the possible organization of computations in biological neural systems has some interesting consequences for the type of learning rules that would be needed to explain the self-organization of such neural circuits.  Finally, our fast and noise-robust implementation of sigmoidal neural nets via temporal coding points to possible new ways of implementing sigmoidal neural nets with pulse stream VLSI.

 

Download Compressed Postscript