CTRNN Parameter Learning using Differential Evolution

Authors:
Ivanoe De Falco;Antonio Della Cioppa;Francesco Donnarumma;Domenico Maisto;Roberto Prevete;Ernesto Tarantino
Affiliations:
ICAR-CNR, Naples, Italy-ivanoe.defalco@na.icar.cnr.it;DIIIE, Università di Salerno-adellacioppa@unisa.it;Università di Napoli Federico II-donnarumma@na.infn.it;ICAR-CNR, Naples, Italy-domenico.maisto@na.icar.cnr.it;Università di Napoli Federico II-prevete@na.infn.it;ICAR-CNR, Naples, Italy-ernesto.tarantino@na.icar.cnr.it
Venue:
Proceedings of the 2008 conference on ECAI 2008: 18th European Conference on Artificial Intelligence
Year:
2008

Citing 3
Cited 1

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

Neural Networks
Sequential behavior and learning in evolved dynamical neural networks

Adaptive Behavior
Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series)

Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series)

A robotic scenario for programmable fixed-weight neural networks exhibiting multiple behaviors

ICANNGA'11 Proceedings of the 10th international conference on Adaptive and natural computing algorithms - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Target behaviours can be achieved by finding suitable parameters for Continuous Time Recurrent Neural Networks (CTRNNs) used as agent control systems. Differential Evolution (DE) has been deployed to search parameter space of CTRNNs and overcome granularity, boundedness and blocking limitations. In this paper we provide initial support for DE in the context of two sample learning problems.