1. Variants of learning algorithm based on Kolmogorov theorem
- Creator:
- Neruda, Roman, Arnošt, Štědrý, and Drkošová, Jitka
- Format:
- bez média and svazek
- Type:
- model:article and TEXT
- Subject:
- Kolmogorov networks, approximation theory, and parallel algorithms
- Language:
- English
- Description:
- 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 impleinentation. A novel approach to parallelization is presented which combines our previous rcsnlts in order to achieve higher parallel speed-up.
- Rights:
- http://creativecommons.org/publicdomain/mark/1.0/ and policy:public