Genetic Programming of Augmenting Topologies for Hypercube-Based Indirect Encoding of Artificial Neural Networks
- Cite this paper as:
- Drchal J., Šnorek M. (2013) Genetic Programming of Augmenting Topologies for Hypercube-Based Indirect Encoding of Artificial Neural Networks. In: Snášel V., Abraham A., Corchado E. (eds) Soft Computing Models in Industrial and Environmental Applications. Advances in Intelligent Systems and Computing, vol 188. Springer, Berlin, Heidelberg
In this paper we present a novel algorithm called GPAT (Genetic Programming of Augmenting Topologies) which evolves Genetic Programming (GP) trees in a similar way as a well-established neuro-evolutionary algorithm NEAT (NeuroEvolution of Augmenting Topologies) does. The evolution starts from a minimal form and gradually adds structure as needed. A niching evolutionary algorithm is used to protect individuals of a variable complexity in a single population. Although GPAT is a general approach we employ it mainly to evolve artificial neural networks by means of Hypercube-based indirect encoding which is an approach allowing for evolution of large-scale neural networks having theoretically unlimited size. We perform also experiments for directly encoded problems. The results show that GPAT outperforms both GP and NEAT taking the best of both.
Unable to display preview. Download preview PDF.