Storage Capacities of Twin-Multistate Quaternion Hopfield Neural Networks

A twin-multistate quaternion Hopfield neural network (TMQHNN) is a multistate Hopfield model and can store multilevel information, such as image data. Storage capacity is an important problem of Hopfield neural networks. Jankowski et al. approximated the crosstalk terms of complex-valued Hopfield ne...

Descripción completa

Detalles Bibliográficos
Autor principal: Kobayashi, Masaki
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2018
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6236997/
https://www.ncbi.nlm.nih.gov/pubmed/30515194
http://dx.doi.org/10.1155/2018/1275290
_version_ 1783371129099911168
author Kobayashi, Masaki
author_facet Kobayashi, Masaki
author_sort Kobayashi, Masaki
collection PubMed
description A twin-multistate quaternion Hopfield neural network (TMQHNN) is a multistate Hopfield model and can store multilevel information, such as image data. Storage capacity is an important problem of Hopfield neural networks. Jankowski et al. approximated the crosstalk terms of complex-valued Hopfield neural networks (CHNNs) by the 2-dimensional normal distributions and evaluated their storage capacities. In this work, we evaluate the storage capacities of TMQHNNs based on their idea.
format Online
Article
Text
id pubmed-6236997
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher Hindawi
record_format MEDLINE/PubMed
spelling pubmed-62369972018-12-04 Storage Capacities of Twin-Multistate Quaternion Hopfield Neural Networks Kobayashi, Masaki Comput Intell Neurosci Research Article A twin-multistate quaternion Hopfield neural network (TMQHNN) is a multistate Hopfield model and can store multilevel information, such as image data. Storage capacity is an important problem of Hopfield neural networks. Jankowski et al. approximated the crosstalk terms of complex-valued Hopfield neural networks (CHNNs) by the 2-dimensional normal distributions and evaluated their storage capacities. In this work, we evaluate the storage capacities of TMQHNNs based on their idea. Hindawi 2018-11-01 /pmc/articles/PMC6236997/ /pubmed/30515194 http://dx.doi.org/10.1155/2018/1275290 Text en Copyright © 2018 Masaki Kobayashi. http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Kobayashi, Masaki
Storage Capacities of Twin-Multistate Quaternion Hopfield Neural Networks
title Storage Capacities of Twin-Multistate Quaternion Hopfield Neural Networks
title_full Storage Capacities of Twin-Multistate Quaternion Hopfield Neural Networks
title_fullStr Storage Capacities of Twin-Multistate Quaternion Hopfield Neural Networks
title_full_unstemmed Storage Capacities of Twin-Multistate Quaternion Hopfield Neural Networks
title_short Storage Capacities of Twin-Multistate Quaternion Hopfield Neural Networks
title_sort storage capacities of twin-multistate quaternion hopfield neural networks
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6236997/
https://www.ncbi.nlm.nih.gov/pubmed/30515194
http://dx.doi.org/10.1155/2018/1275290
work_keys_str_mv AT kobayashimasaki storagecapacitiesoftwinmultistatequaternionhopfieldneuralnetworks

Ejemplares similares