Neuroevolution on the Edge of Chaos

Abstract

Echo state networks represent a special type of recurrent neural networks. Recent papers stated that the echo state networks maximize their computational performance on the transition between order and chaos, the so-called edge of chaos. This work confirms this statement in a comprehensive set of experiments. Furthermore, the echo state networks are compared to networks evolved via neuroevolution. The evolved networks outperform the echo state networks, however, the evolution consumes significant computational resources. It is demonstrated that echo state networks with local connections combine the best of both worlds, the simplicity of random echo state networks and the performance of evolved networks. Finally, it is shown that evolution tends to stay close to the ordered side of the edge of chaos.

To appear in Proceedings of the Genetic and Evolutionary Computation Conference 2017 (GECCO '17)

References in corpus (3)

• On the difficulty of training Recurrent Neural Networks
• JIDT: An information-theoretic toolkit for studying the dynamics of complex systems
• Local information transfer as a spatiotemporal filter for complex systems

Cited by in corpus (1)

• Hyperparameter Tuning in Echo State Networks