Center-Crossing Recurrent Neural Networks for the Evolution of Rhythmic Behavior

A center-crossing recurrent neural network is one in which the null-(hyper)surfaces of each neuron intersect at their exact centers of symmetry, ensuring that each neuron’s activation function is centered over the range of net inputs that it receives. We demonstrate that relative to a random initial population, seeding the initial population of an evolutionary search with center-crossing networks signiŽficantly improves both the frequency and the speed with which high-fiŽtness oscillatory circuits evolve on a simple walking task. The improvement is especially striking at low mutation variances. Our results suggest that seeding with center-crossing networks may often be beneŽficial, since a wider range of dynamics is more likely to be easily accessible from a population of center-crossing networks than from a population of random networks.

Mathayomchan, B. and Beer, R.D. (2002). Center-crossing recurrent neural networks for the evolution of rhythmic behavior. Neural Computation 14:2043-2051.


, , ,

  1. Leave a comment

Leave a Reply

Please log in using one of these methods to post your comment: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: