Topology Learning Solved by Extended Objects: A Neural Network Model
Abstract
It is shown that local, extended objects of a metrical topological space shape the receptive fields of competitive neurons to local filters. Self-organized topology learning is then solved with the help of Hebbian learning together with extended objects that provide unique information about neighborhood relations. A topographical map is deduced and is used to speed up further adaptation in a changing environment with the help of Kohonen-type learning that teaches the neighbors of winning neurons as well.
Cite
Text
Szepesvári et al. "Topology Learning Solved by Extended Objects: A Neural Network Model." Neural Computation, 1994. doi:10.1162/NECO.1994.6.3.441Markdown
[Szepesvári et al. "Topology Learning Solved by Extended Objects: A Neural Network Model." Neural Computation, 1994.](https://mlanthology.org/neco/1994/szepesvari1994neco-topology/) doi:10.1162/NECO.1994.6.3.441BibTeX
@article{szepesvari1994neco-topology,
title = {{Topology Learning Solved by Extended Objects: A Neural Network Model}},
author = {Szepesvári, Csaba and Balázs, László and Lörincz, András},
journal = {Neural Computation},
year = {1994},
pages = {441-458},
doi = {10.1162/NECO.1994.6.3.441},
volume = {6},
url = {https://mlanthology.org/neco/1994/szepesvari1994neco-topology/}
}