Abstract
This work introduces a new algorithm called the Self-Organizing Neural Network (SONN), and demonstrates its use in a system identification task. The algorithm constructs a network, chooses the neuron functions, and adjusts the weights. Here, it is compared to the Back-Propagation algorithm in the identification of the chaotic time series. The results show that SONN constructs a simpler, more accurate model, requiring less training data and epochs. The algorithm can also be applied as a classifier.
Date of this Version
6-1-1989
COinS