Training Neural Networks by Stochastic Optimisation

Authors

  • A. Verikas
  • A. Gelzinis
  • M. Bacauskiene

Abstract

We present a stochastic learning algorithm for neural networks. The algorithm does not make any assumptions about transfer functions of individual neurons and does not depend on a functional form of an error measure. The algo-rithm uses a random step of varying size to adapt weights. The average size of the step decreases during learning.

Published

1998-03-07

How to Cite

Verikas, A., Gelzinis, A., & Bacauskiene, M. (1998). Training Neural Networks by Stochastic Optimisation. Elektronika Ir Elektrotechnika, 15(2). Retrieved from https://eejournal.ktu.lt/index.php/elt/article/view/15994

Issue

Vol. 15 No. 2 (1998)

Section

Articles

License

The copyright for the paper in this journal is retained by the author(s) with the first publication right granted to the journal. The authors agree to the Creative Commons Attribution 4.0 (CC BY 4.0) agreement under which the paper in the Journal is licensed.

By virtue of their appearance in this open access journal, papers are free to use with proper attribution in educational and other non-commercial settings with an acknowledgement of the initial publication in the journal.