by R Malaka and S Buck
Abstract:
Most artificial neural networks used in practical applications are based on simple neuron types in a multi-layer architecture. Here, we propose to solve optimization problems using a fully recurrent network of spiking neurons mimicking the response behavior of biological neurons. Such networks can compute a series of different solutions for a given problem and converge into a periodical sequence of such solutions. The goal of this paper is to prove that neural networks like the SRM (Spike Response Model) are able to solve nonlinear optimization problems. We demonstrate this for the traveling salesman problem. Our network model is able to compute multiple solutions and can use its dynamics to leave local minima in which classical models would be stuck. For adapting the model, we introduce a suitable network architecture and show how to encode the problem directly into the network weights.
Reference:
Solving Nonlinear Optimization Problems Using Networks Of Spiking Neurons (R Malaka and S Buck), In IEEE International Joint Conference on Neural Networks, volume 6, 2000.
Bibtex Entry:
@inproceedings{malaka_solving_2000,
author = {R Malaka and S Buck},
title = {Solving Nonlinear Optimization Problems Using Networks Of Spiking
Neurons},
booktitle = {{IEEE} International Joint Conference on Neural Networks},
year = {2000},
volume = {6},
pages = {486–491},
abstract = {Most artificial neural networks used in practical applications are
based on simple neuron types in a multi-layer architecture. Here,
we propose to solve optimization problems using a fully recurrent
network of spiking neurons mimicking the response behavior of biological
neurons. Such networks can compute a series of different solutions
for a given problem and converge into a periodical sequence of such
solutions. The goal of this paper is to prove that neural networks
like the {SRM} (Spike Response Model) are able to solve nonlinear
optimization problems. We demonstrate this for the traveling salesman
problem. Our network model is able to compute multiple solutions
and can use its dynamics to leave local minima in which classical
models would be stuck. For adapting the model, we introduce a suitable
network architecture and show how to encode the problem directly
into the network weights.},
}