Informatica logo


Login Register

  1. Home
  2. Issues
  3. Volume 5, Issues 1-2 (1994)
  4. Searching for minimum in neural networks

Informatica

Information Submit your article For Referees Help ATTENTION!
  • Article info
  • Related articles
  • More
    Article info Related articles

Searching for minimum in neural networks
Volume 5, Issues 1-2 (1994), pp. 241–255
Vytautas Vyšniauskas  

Authors

 
Placeholder
https://doi.org/10.3233/INF-1994-51-214
Pub. online: 1 January 1994      Type: Research Article     

Published
1 January 1994

Abstract

Neural networks are often characterized as highly nonlinear systems of fairly large amount of parameters (in order of 103 – 104). This fact makes the optimization of parameters to be a nontrivial problem. But the astonishing moment is that the local optimization technique is widely used and yields reliable convergence in many cases. Obviously, the optimization of neural networks is high-dimensional, multi-extremal problem, so, as usual, the global optimization methods would be applied in this case. On the basis of Perceptron-like unit (which is the building block for the most architectures of neural networks) we analyze why the local optimization technique is so successful in the field of neural networks. The result is that a linear approximation of the neural network can be sufficient to evaluate the start point for the local optimization procedure in the nonlinear regime. This result can help in developing faster and more robust algorithms for the optimization of neural network parameters.

Related articles PDF XML
Related articles PDF XML

Copyright
No copyright data available.

Keywords
neural networks optimization theory pattern recognition

Metrics
since January 2020
635

Article info
views

0

Full article
views

440

PDF
downloads

162

XML
downloads

Export citation

Copy and paste formatted citation
Placeholder

Download citation in file


Share


RSS

INFORMATICA

  • Online ISSN: 1822-8844
  • Print ISSN: 0868-4952
  • Copyright © 2023 Vilnius University

About

  • About journal

For contributors

  • OA Policy
  • Submit your article
  • Instructions for Referees
    •  

    •  

Contact us

  • Institute of Data Science and Digital Technologies
  • Vilnius University

    Akademijos St. 4

    08412 Vilnius, Lithuania

    Phone: (+370 5) 2109 338

    E-mail: informatica@mii.vu.lt

    https://informatica.vu.lt/journal/INFORMATICA
Powered by PubliMill  •  Privacy policy