An Adaptive Time-delay Neural Network Training using Parallel Genetic Algorithms in Time-series Prediction and Classification
Titel:
An Adaptive Time-delay Neural Network Training using Parallel Genetic Algorithms in Time-series Prediction and Classification
Auteur:
A. Ourdighi A. Benyettou
Verschenen in:
Journal of applied sciences
Paginering:
Jaargang 10 (2010) nr. 18 pagina's 2115-2120
Jaar:
2010
Inhoud:
In this study, we present an Adaptive Time Delay Neural Network (ATNN) training based in parallel genetic algorithms and local search method in a comparative study which applied in several problems. Usually, the ATNN training used a temporal variant of gradient descent algorithm and universal approximation function and consequently inherits problematic of parameters initialization and traps into local minimum. Besides, the algorithm was based on the peculiarity to adapt not only the synaptic weight but also each delay of interconnection which singularizes the ATNN architecture. This adaptation paradigm offers more flexibility for the network to attain the optimal time-delays and to achieve more accurate pattern mapping and recognition than is the case of using arbitrary fixed delays, as has been done previously by Time Delay Neural Network (TDNN). Also, this principal provoked instability on converging process of gradient descent rules and affected the results. So, our aim is to replace discriminated method algorithm to stochastic approach, the training will be base on parallel genetic algorithms: multiple-deme parallel genetic algorithms. The important characteristics of multiple-deme parallel GAs are the use of a few relatively large subpopulations and migration. The model was tested on Time series prediction of Mackey-Glass a chaotic series and phonetic classification. Index Terms- Adaptive Time-Delay Neural Network (ATNN), Adaptable delay, Synaptic weight, Multiple-deme parallel genetic algorithms, local minimum, immigration.
Uitgever:
Asian Network for Scientific Information (provided by DOAJ)
Tijdschrift beschrijving