Center-crossing recurrent neural networks for the evolution of rhythmic behavior

Authors:
Boonyanit Mathayomchan;Randall D. Beer
Affiliations:
Department of Electrical Engineering and Computer Science, Case Western Reserve University, Cleveland, OH;Departments of Electrical Engineering and Computer Science and of Biology, Case Western Reserve University, Cleveland, OH
Venue:
Neural Computation
Year:
2002

Citing 9
Cited 13

Oscillations and synchronization in neural networks: an exploration of the labeling

International Journal of Neural Systems
Original Contribution: Stability of fixed points and periodic orbits and bifurcations in analog neural networks

Neural Networks
Original Contribution: Approximation of dynamical systems by continuous time recurrent neural networks

Neural Networks
Evolving dynamical neural networks for adaptive behavior

Adaptive Behavior
Explorations in evolutionary robotics

Adaptive Behavior
On the dynamics of small continuous-time recurrent neural networks

Adaptive Behavior - Special issue on computational neuroethology
Evolutionary algorithms in theory and practice: evolution strategies, evolutionary programming, genetic algorithms

Evolutionary algorithms in theory and practice: evolution strategies, evolutionary programming, genetic algorithms
An investigation into the evolution of communication

Adaptive Behavior
Near-saddle-node bifurcation behavior as dynamics in working memory for goal-directed behavior

Neural Computation

Evolution of Neural Architecture Fitting Environmental Dynamics

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Flexible Couplings: Diffusing Neuromodulators and Adaptive Robotics

Artificial Life
Parameter space structure of continuous-time recurrent neural networks

Neural Computation
Neural Noise Induces the Evolution of Robust Behaviour by Avoiding Non-functional Bifurcations

SAB '08 Proceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats
Monostable Controllers for Adaptive Behaviour

SAB '08 Proceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats
Evolution of neural networks for active control of tethered airfoils

ECAL'07 Proceedings of the 9th European conference on Advances in artificial life
Feathered flyer: integrating morphological computation and sensory reflexes into a physically simulated flapping-wing robot for robust flight manoeuvre

ECAL'07 Proceedings of the 9th European conference on Advances in artificial life
Neural uncertainty and sensorimotor robustness

ECAL'07 Proceedings of the 9th European conference on Advances in artificial life
Direct programming of a central pattern generator for periodic motions by touching

Robotics and Autonomous Systems
Flexible and multistable pattern generation by evolving constrained plastic neurocontrollers

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Evolving the walking behaviour of a 12 DOF quadruped using a distributed neural architecture

BioADIT'06 Proceedings of the Second international conference on Biologically Inspired Approaches to Advanced Information Technology
Biped locomotion control with evolved adaptive center-crossing continuous time recurrent neural networks

Neurocomputing
Evolving plastic neural networks for online learning: review and future directions

AI'12 Proceedings of the 25th Australasian joint conference on Advances in Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

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 significantly improves both the frequency and the speed with which high-fitness 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 beneficial, 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.