Self Organizing Neural Networks for the Identification Problem

Abstract

This work introduces a new method called Self Organizing Neural Network (SONN) algorithm and demonstrates its use in a system identification task. The algorithm constructs the network, chooses the neuron functions, and adjusts the weights. It is compared to the Back-Propagation algorithm in the identification of the chaotic time series. The results shows that SONN constructs a simpler, more accurate model. requiring less training data and epochs. The algorithm can be applied and generalized to appilications as a classifier.

Cite

Text

Tenorio and Lee. "Self Organizing Neural Networks for the Identification Problem." Neural Information Processing Systems, 1988.

Markdown

[Tenorio and Lee. "Self Organizing Neural Networks for the Identification Problem." Neural Information Processing Systems, 1988.](https://mlanthology.org/neurips/1988/tenorio1988neurips-self/)

BibTeX

@inproceedings{tenorio1988neurips-self,
  title     = {{Self Organizing Neural Networks for the Identification Problem}},
  author    = {Tenorio, Manoel Fernando and Lee, Wei-Tsih},
  booktitle = {Neural Information Processing Systems},
  year      = {1988},
  pages     = {57-64},
  url       = {https://mlanthology.org/neurips/1988/tenorio1988neurips-self/}
}