Abstract. We present a system for automatically evolving neural networks as physics-based locomotion controllers for humanoid characters. Our approach provides two key features: (a...
This case study demonstrates how the synthesis and the analysis of minimal recurrent neural robot control provide insights into the exploration of embodiment. By using structural e...
Evolutionary design of neural networks has shown a great potential as a powerful optimization tool. However, most evolutionary neural networks have not taken advantage of the fact ...
In this paper we present the growing hierarchical self-organizing map. This dynamically growing neural network model evolves into a hierarchical structure according to the requirem...
Neuro-evolution and computational neuroscience are two scientific domains that produce surprisingly different artificial neural networks. Inspired by the “toolbox” used by ...