Variants of Learning Algorithm Based on Kolmogorov Theorem

  • Authors:
  • Roman Neruda;Arnost Stedrý;Jitka Drkosová

  • Affiliations:
  • -;-;-

  • Venue:
  • ICCS '02 Proceedings of the International Conference on Computational Science-Part III
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

A thorough analysis of theoretical and computational properties of kolmogorov learning algorithm for feedforward neural networks lead us to proposal of efficient sequential and parallel implementation. A novel approach to parallelization which combines our previous results in order to achieve higher parallel speedup is presented.