Kolmogorov's theorem and multilayer neural networks
Neural Networks
Implementation of Kolmogorov Learning Algorithm for Feedforward Neural Networks
ICCS '01 Proceedings of the International Conference on Computational Science-Part II
Dealing with biometric multi-dimensionality through chaotic neural network methodology
International Journal of Information Technology and Management
Using kolmogorov inspired gates for low power nanoelectronics
IWANN'05 Proceedings of the 8th international conference on Artificial Neural Networks: computational Intelligence and Bioinspired Systems
MOEA/D assisted by rbf networks for expensive multi-objective optimization problems
Proceedings of the 15th annual conference on Genetic and evolutionary computation
| Hi-index | 0.00 |
Based on constructions of Kalmogorov and an earlier refinement of the author, we use a sequence of integrally independent positive numbers to construct a continuous function @j(x) having the following property: Every real-valued uniformly continuous function f(x"1, ..., x"n) of n = 2 variables can be obtained as a superposition of continuousfunctions of one variable based on weighted sums of translates of the fixedfunction @j(x) that is independent of the number of variables n. From this is obtained a stronger version of the Hecht-Nielsen three-layer feedforward neural network for implementing f(x"1, ..., x"n).