Evolving A-Type Artificial Neural Networks

Details Evolving A-Type Artificial Neural Networks Evolving A-Type Artificial Neural Networks

2011-08-07

arxiv.org/abs/1108.1530v1

Computer Science

Neural and Evolutionary Computing

21 pages. To appear in Evolutionary Intelligence

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Evolving A-Type Artificial Neural Networks does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Evolving A-Type Artificial Neural Networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Evolving A-Type Artificial Neural Networks will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-707293