|
NeuroCOLT
Technical Report NC-TR-99-038
A Simple Model for Neural Computation
with Firing Rates and Firing Correlations
Wolfgang Maass
Institute for Theoretical Computer Science,
Technische Universität Graz
Received:22-MAR-1999
Abstract
A simple extension of standard neural network models
is introduced that provides a model for neural computations that involve
both firing rates and firing correlations. Such extension appears
to be useful since it has been shown that firing correlations play
a significant computational role in many biological neural systems.
Standard neural network models are only suitable for describing neural
computations in terms of firing rates. The resulting extended
neural network models are still relatively simple, so that their computational
power
can be analyzed theoretically. We prove rigorous separation results,
which show that the use of firing correlations in addition to firing
rates can drastically increase the computational power of a neural
network. On the side, one of our separation results also throws
new light on a question that involves just standard neural network
models: We prove that the gap between the computational power of high-order
and first-order neural nets is substantially larger than shown previously.
Download Compressed Postscript
|