Evolving A-Type Artificial Neural Networks

TL;DR

This paper explores the evolution of A-type artificial neural networks capable of processing binary sequences, introducing an evolutionary algorithm with graph manipulations that effectively learns functions, outperforming random search on benchmark tasks.

Contribution

It refines Turing's A-type neural network concept, developing an evolutionary algorithm with mutation and crossover for function representation, and demonstrates its effectiveness on benchmark tasks.

Findings

Algorithm outperforms random search in benchmark tasks.

Crossover improves performance over mutation-only approach.

A-types successfully represent functions via binary sequence processing.

Abstract

We investigate Turing's notion of an A-type artificial neural network. We study a refinement of Turing's original idea, motivated by work of Teuscher, Bull, Preen and Copeland. Our A-types can process binary data by accepting and outputting sequences of binary vectors; hence we can associate a function to an A-type, and we say the A-type {\em represents} the function. There are two modes of data processing: clamped and sequential. We describe an evolutionary algorithm, involving graph-theoretic manipulations of A-types, which searches for A-types representing a given function. The algorithm uses both mutation and crossover operators. We implemented the algorithm and applied it to three benchmark tasks. We found that the algorithm performed much better than a random search. For two out of the three tasks, the algorithm with crossover performed better than a mutation-only version.