Title :
Training multiple-layer perceptrons to recognize attractors
Author :
Greenwood, Garrison W.
Author_Institution :
Dept. of Electr. & Comput. Eng., Western Michigan Univ., Kalamazoo, MI, USA
fDate :
11/1/1997 12:00:00 AM
Abstract :
Determining the long-term behavior in dynamical systems is an area of intense research interest. In this paper, a multilayer perceptron is used to perform this task. The network is trained using an evolution strategy. A comparison against backpropagation-trained networks was performed, and the results indicate evolution strategies produce better performing networks
Keywords :
chaos; learning (artificial intelligence); multilayer perceptrons; pattern recognition; time series; attractor recognition; chaotic systems; dynamical systems; evolution strategy; learning; multilayer perceptron; time series; Algorithm design and analysis; Backpropagation; Chaos; Computer architecture; Equations; Neurons; Pattern recognition; Time series analysis;
Journal_Title :
Evolutionary Computation, IEEE Transactions on
DOI :
10.1109/4235.687884
