A Note on Topology Preservation in Classification, and the Construction of a Universal Neuron Grid
Neural and Evolutionary Computing
2018-02-02 v4 Artificial Intelligence
Adaptation and Self-Organizing Systems
Machine Learning
Abstract
It will be shown that according to theorems of K. Menger, every neuron grid if identified with a curve is able to preserve the adopted qualitative structure of a data space. Furthermore, if this identification is made, the neuron grid structure can always be mapped to a subset of a universal neuron grid which is constructable in three space dimensions. Conclusions will be drawn for established neuron grid types as well as neural fields.
Keywords
Cite
@article{arxiv.1308.1603,
title = {A Note on Topology Preservation in Classification, and the Construction of a Universal Neuron Grid},
author = {Dietmar Volz},
journal= {arXiv preprint arXiv:1308.1603},
year = {2018}
}