|
NeuroCOLT
Technical Report NC-TR-99-036
Spatial
and Temporal Pattern Analysis via Spiking Neurons
Thomas Natschläger, Berthold Ruf
Institute for Theoretical Computer Science
Technische Universität Graz
Received:
22-MAR-99
Abstract
Spiking neurons, receiving temporally encoded inputs, can compute
radial basis functions (RBFs) by storing the relevant information
in their delays. In this paper we show how these delays can be learned
using exclusively locally available information (basically the time
difference between the pre- and postsynaptic spike). Our approach
gives rise to a biologically plausible algorithm for finding clusters
in a high dimensional input space with networks of spiking neurons,
even if the environment is changing dynamically. Furthermore, we show
that our learning mechanism makes it possible that such RBF neurons
can perform some kind of feature extraction where they recognize that
only certain input coordinates carry relevant information. Finally
we demonstrate that this model allows the recognition of temporal
sequences even if they are distorted in various ways.
Download Compressed Postscript
|