Connection and Coordination: The Interplay Between Architecture and Dynamics in Evolved Model Pattern Generators

Authors:
Sean Psujek;Jeffrey Ames;Randall D. Beer
Affiliations:
Department of Biology, Case Western Reserve University, Cleveland, OH 44106, U.S.A.;Department of Electrical Engineering and Computer Science, Case Western Reserve University, Cleveland, OH 44106, U.S.A.;Department of Biology and Department of Electrical Engineering and Computer Science, Case Western Reserve University, Cleveland, OH 44106, U.S.A.
Venue:
Neural Computation
Year:
2006

Citing 7
Cited 4

Evolving dynamical neural networks for adaptive behavior

Adaptive Behavior
Automatic definition of modular neural networks

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
Classification of temporal patterns in dynamic biological networks

Neural Computation
Evolving neural networks through augmenting topologies

Evolutionary Computation
Evolution and development of neural controllers for locomotion, gradient-following, and obstacle-avoidance in artificial insects

IEEE Transactions on Neural Networks

Parameter space structure of continuous-time recurrent neural networks

Neural Computation
Reflex-oscillations in evolved single leg neurocontrollers for walking machines

Natural Computing: an international journal
Preliminary investigations on the evolvability of a non-spatial GasNet model

ECAL'07 Proceedings of the 9th European conference on Advances in artificial life
Fitness Space Structure of a Neuromechanical System

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

We undertake a systematic study of the role of neural architecture in shaping the dynamics of evolved model pattern generators for a walking task. First, we consider the minimum number of connections necessary to achieve high performance on this task. Next, we identify architectural motifs associated with high fitness. We then examine how high-fitness architectures differ in their ability to evolve. Finally, we demonstrate the existence of distinct parameter subgroups in some architectures and show that these subgroups are characterized by differences in neuron excitabilities and connection signs.