Generation of Two-Layer Monotonic Functions
Neural and Evolutionary Computing
2012-11-06 v1
Abstract
The problem of implementing a class of functions with particular conditions by using monotonic multilayer functions is considered. A genetic algorithm is used to create monotonic functions of a certain class, and these are implemented with two-layer monotonic functions. The existence of a solution to the given problem suggests that from two monotone functions, a monotonic function with the same dimensions can be created. A new algorithm based on the genetic algorithm is proposed, which easily implemented two-layer monotonic functions of a specific class for up to six variables.
Cite
@article{arxiv.1211.0660,
title = {Generation of Two-Layer Monotonic Functions},
author = {Yukihiro Kamada and Kiyonori Miyasaki},
journal= {arXiv preprint arXiv:1211.0660},
year = {2012}
}
Comments
5 pages