|
NeuroCOLT
Technical Report NC-TR-99-050
Efficient
Computation in Networks of Spiking Neurons
- Simulations and Theory
Thomas Natschläger
Institute for Theoretical Computer Science
Technische Universität Graz
Abstract
One of the most prominent
features of biological neural systems is that individual neurons communicate
via short electrical pulses, the so called action potentials or spikes.
In this thesis we investigate possible mechanisms which can in principle
explain how complex computations in spiking neural networks (SNN)
can be performed very fast, i.e. within a few 10 milliseconds. Some
of these models are based on the assumption that relevant information
is encoded by the timing of individual spikes (temporal coding).
We will also discuss a model which is based on a population code and
still is able to perform fast complex computations. In their natural
environment biological neural systems have to process signals with
a rich temporal structure. Hence it is an interesting question how
neural systems process time series. In this context we explore possible
links between biophysical characteristics of single neurons (refractory
behavior, connectivity, time course of postsynaptic potentials) and
synapses (unreliability, dynamics) on the one hand and possible computations
on times series on the other hand. Furthermore we describe a general
model of computation that exploits dynamic synapses. This model provides
a general framework for understanding how neural systems process time-varying
signals.
Download Compressed Postscript
|