19 August 1993 Evolving recurrent perceptrons
Author Affiliations +
This woit investigates the application of evolutionary programming, a multi-agent stochastic search technique, to the generation of recurrent perceptrons (nonlinear hR filters) for time-series prediction tasks. The evolutionary programming paradigm is discussed and analogies are made to classical stochastic optimization methods. A hybrid optimization scheme is proposed based on multi-agent and single-agent random optimization techniques. This method is then used to determine both the model order and weight coefficients of linear, nonlinear, and parallel linear-nonlinear nextstep predictors. The AIC is used as the cost function to score each candidate solution.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
John R. McDonnell, John R. McDonnell, Donald E. Waagen, Donald E. Waagen, } "Evolving recurrent perceptrons", Proc. SPIE 1966, Science of Artificial Neural Networks II, (19 August 1993); doi: 10.1117/12.152634; https://doi.org/10.1117/12.152634

Back to Top