Title :
Evolving recurrent perceptrons for time-series modeling
Author :
McDonnell, J.R. ; Waagen, D.
Author_Institution :
RDT&E Div., NCCOSC, San Diego, CA, USA
fDate :
1/1/1994 12:00:00 AM
Abstract :
Evolutionary programming, a systematic multi-agent stochastic search technique, is used to generate recurrent perceptrons (nonlinear IIR filters). A hybrid optimization scheme is proposed that embeds a single-agent stochastic search technique, the method of Solis and Wets, into the evolutionary programming paradigm. The proposed hybrid optimization approach is further augmented by “blending” randomly selected parent vectors to create additional offspring. The first part of this work investigates the performance of the suggested hybrid stochastic search method. After demonstration on the Bohachevsky and Rosenbrock response surfaces, the hybrid stochastic optimization approach is applied in determining both the model order and the coefficients of recurrent perceptron time-series models. An information criterion is used to evaluate each recurrent perceptron structure as a candidate solution. It is speculated that the stochastic training method implemented in this study for training recurrent perceptrons can be used to train perceptron networks that have radically recurrent architectures
Keywords :
digital filters; learning (artificial intelligence); optimisation; recurrent neural nets; search problems; time series; Bohachevsky and Rosenbrock response surfaces; evolutionary programming; hybrid optimization; information criterion; multi-agent stochastic search technique; nonlinear IIR filters; recurrent perceptrons; stochastic training method; time-series modeling; Delay; Finite impulse response filter; Genetic programming; IIR filters; Neural networks; Optimization methods; Search methods; Stochastic processes; Stochastic systems; Transversal filters;
Journal_Title :
Neural Networks, IEEE Transactions on