Loading…

A Novel Self-Organizing Fuzzy Neural Network to Learn and Mimic Habitual Sequential Tasks

In this article, a new self-organizing fuzzy neural network (FNN) model is presented which is able to simultaneously and accurately learn and reproduce different sequences. Multiple sequence learning is important in performing habitual and skillful tasks, such as writing, signing signatures, and pla...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on cybernetics 2022-01, Vol.52 (1), p.323-332
Main Authors: Salimi-Badr, Armin, Ebadzadeh, Mohammad Mehdi
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c349t-14f231c9534aaac8ef06f7e4a38b1e7e02ad5ef2b7f5209cc1f328c4ddd46263
cites cdi_FETCH-LOGICAL-c349t-14f231c9534aaac8ef06f7e4a38b1e7e02ad5ef2b7f5209cc1f328c4ddd46263
container_end_page 332
container_issue 1
container_start_page 323
container_title IEEE transactions on cybernetics
container_volume 52
creator Salimi-Badr, Armin
Ebadzadeh, Mohammad Mehdi
description In this article, a new self-organizing fuzzy neural network (FNN) model is presented which is able to simultaneously and accurately learn and reproduce different sequences. Multiple sequence learning is important in performing habitual and skillful tasks, such as writing, signing signatures, and playing piano. Generally, it is indispensable for pattern generation applications. Since multiple sequences have similar parts, local information such as some previous samples is not sufficient to efficiently reproduce them. Instead, it is necessary to consider global and discriminative information, maybe in the very initial samples of each sequence, to first recognize them, and then predict their next sample based on the current local information. Therefore, the structure of the proposed network consists of two parts: 1) sequence identifier, which computes a novel sequence identity value based on initial samples of a sequence, and detects the sequence identity based on proper fuzzy rules and 2) sequence locator , which locates the input sample in the sequence. Therefore, by integrating outputs of these two parts in fuzzy rules, the network is able to produce the proper output based on the current state of each sequence. To learn the proposed structure, a gradual learning procedure is proposed. First, learning is performed by adding new fuzzy rules, based on coverage measure, using available correct data. Next, the initialized parameters are fine-tuned, by the gradient descent algorithm, based on fed back approximated network output as the next input. The proposed method has a dynamic structure able to learn new sequences online. Finally, to investigate the effectiveness of the presented approach, it is used to simultaneously learn and reproduce multiple sequences in different applications, including sequences with similar parts, different patterns, and writing different letters. The performance of the proposed method is evaluated and compared with other existing methods, including the adaptive network-based fuzzy inference system, GDFNN, CFNN, and long short-term memory (LSTM). According to these experiments, the proposed method outperforms traditional FNNs and LSTM in learning multiple sequences.
doi_str_mv 10.1109/TCYB.2020.2984646
format article
fullrecord <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_proquest_journals_2619018306</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9082168</ieee_id><sourcerecordid>2619018306</sourcerecordid><originalsourceid>FETCH-LOGICAL-c349t-14f231c9534aaac8ef06f7e4a38b1e7e02ad5ef2b7f5209cc1f328c4ddd46263</originalsourceid><addsrcrecordid>eNpdkU1LAzEQhoMoKuoPEEECXrxszcduNjlq8Qtqe7AXTyHNTiS63dVkV7G_3iytPZjLDMkzL8MThE4pGVFK1NV8_HIzYoSREVMyF7nYQYeMCpkxVha7216UB-gkxjeSjkxXSu6jA854IUqhDtHLNZ62X1DjZ6hdNguvpvEr37ziu361-sFT6IOpU-m-2_COuxZPwIQGm6bCT37pLX4wC9_1Zgj47KHpfGrnJr7HY7TnTB3hZFOP0Pzudj5-yCaz-8fx9SSzPFddRnPHOLWq4LkxxkpwRLgScsPlgkIJhJmqAMcWpSsYUdZSx5m0eVVVuWCCH6HLdexHaNMCsdNLHy3UtWmg7aNmXJWiUIXgCb34h761fWjScpoJqgiVnAyBdE3Z0MYYwOmP4Jcm_GhK9GBeD-b1YF5vzKeZ801yv1hCtZ3485yAszXgAWD7rIgcfon_AjuXhkk</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2619018306</pqid></control><display><type>article</type><title>A Novel Self-Organizing Fuzzy Neural Network to Learn and Mimic Habitual Sequential Tasks</title><source>IEEE Electronic Library (IEL) Journals</source><creator>Salimi-Badr, Armin ; Ebadzadeh, Mohammad Mehdi</creator><creatorcontrib>Salimi-Badr, Armin ; Ebadzadeh, Mohammad Mehdi</creatorcontrib><description>In this article, a new self-organizing fuzzy neural network (FNN) model is presented which is able to simultaneously and accurately learn and reproduce different sequences. Multiple sequence learning is important in performing habitual and skillful tasks, such as writing, signing signatures, and playing piano. Generally, it is indispensable for pattern generation applications. Since multiple sequences have similar parts, local information such as some previous samples is not sufficient to efficiently reproduce them. Instead, it is necessary to consider global and discriminative information, maybe in the very initial samples of each sequence, to first recognize them, and then predict their next sample based on the current local information. Therefore, the structure of the proposed network consists of two parts: 1) sequence identifier, which computes a novel sequence identity value based on initial samples of a sequence, and detects the sequence identity based on proper fuzzy rules and 2) sequence locator , which locates the input sample in the sequence. Therefore, by integrating outputs of these two parts in fuzzy rules, the network is able to produce the proper output based on the current state of each sequence. To learn the proposed structure, a gradual learning procedure is proposed. First, learning is performed by adding new fuzzy rules, based on coverage measure, using available correct data. Next, the initialized parameters are fine-tuned, by the gradient descent algorithm, based on fed back approximated network output as the next input. The proposed method has a dynamic structure able to learn new sequences online. Finally, to investigate the effectiveness of the presented approach, it is used to simultaneously learn and reproduce multiple sequences in different applications, including sequences with similar parts, different patterns, and writing different letters. The performance of the proposed method is evaluated and compared with other existing methods, including the adaptive network-based fuzzy inference system, GDFNN, CFNN, and long short-term memory (LSTM). According to these experiments, the proposed method outperforms traditional FNNs and LSTM in learning multiple sequences.</description><identifier>ISSN: 2168-2267</identifier><identifier>EISSN: 2168-2275</identifier><identifier>DOI: 10.1109/TCYB.2020.2984646</identifier><identifier>PMID: 32356769</identifier><identifier>CODEN: ITCEB8</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Algorithms ; Artificial neural networks ; Fuzzy control ; Fuzzy Logic ; Fuzzy neural networks ; Fuzzy sets ; Gradual learning ; habits ; Learning ; multivariate fuzzy sets ; Neural networks ; Neural Networks, Computer ; Neurons ; Pattern generation ; self-organizing fuzzy neural networks (FNNs) ; sequence learning ; Task analysis ; Trajectory ; Writing</subject><ispartof>IEEE transactions on cybernetics, 2022-01, Vol.52 (1), p.323-332</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c349t-14f231c9534aaac8ef06f7e4a38b1e7e02ad5ef2b7f5209cc1f328c4ddd46263</citedby><cites>FETCH-LOGICAL-c349t-14f231c9534aaac8ef06f7e4a38b1e7e02ad5ef2b7f5209cc1f328c4ddd46263</cites><orcidid>0000-0001-6466-5229 ; 0000-0001-6613-7921</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9082168$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,27922,27923,54794</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/32356769$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Salimi-Badr, Armin</creatorcontrib><creatorcontrib>Ebadzadeh, Mohammad Mehdi</creatorcontrib><title>A Novel Self-Organizing Fuzzy Neural Network to Learn and Mimic Habitual Sequential Tasks</title><title>IEEE transactions on cybernetics</title><addtitle>TCYB</addtitle><addtitle>IEEE Trans Cybern</addtitle><description>In this article, a new self-organizing fuzzy neural network (FNN) model is presented which is able to simultaneously and accurately learn and reproduce different sequences. Multiple sequence learning is important in performing habitual and skillful tasks, such as writing, signing signatures, and playing piano. Generally, it is indispensable for pattern generation applications. Since multiple sequences have similar parts, local information such as some previous samples is not sufficient to efficiently reproduce them. Instead, it is necessary to consider global and discriminative information, maybe in the very initial samples of each sequence, to first recognize them, and then predict their next sample based on the current local information. Therefore, the structure of the proposed network consists of two parts: 1) sequence identifier, which computes a novel sequence identity value based on initial samples of a sequence, and detects the sequence identity based on proper fuzzy rules and 2) sequence locator , which locates the input sample in the sequence. Therefore, by integrating outputs of these two parts in fuzzy rules, the network is able to produce the proper output based on the current state of each sequence. To learn the proposed structure, a gradual learning procedure is proposed. First, learning is performed by adding new fuzzy rules, based on coverage measure, using available correct data. Next, the initialized parameters are fine-tuned, by the gradient descent algorithm, based on fed back approximated network output as the next input. The proposed method has a dynamic structure able to learn new sequences online. Finally, to investigate the effectiveness of the presented approach, it is used to simultaneously learn and reproduce multiple sequences in different applications, including sequences with similar parts, different patterns, and writing different letters. The performance of the proposed method is evaluated and compared with other existing methods, including the adaptive network-based fuzzy inference system, GDFNN, CFNN, and long short-term memory (LSTM). According to these experiments, the proposed method outperforms traditional FNNs and LSTM in learning multiple sequences.</description><subject>Algorithms</subject><subject>Artificial neural networks</subject><subject>Fuzzy control</subject><subject>Fuzzy Logic</subject><subject>Fuzzy neural networks</subject><subject>Fuzzy sets</subject><subject>Gradual learning</subject><subject>habits</subject><subject>Learning</subject><subject>multivariate fuzzy sets</subject><subject>Neural networks</subject><subject>Neural Networks, Computer</subject><subject>Neurons</subject><subject>Pattern generation</subject><subject>self-organizing fuzzy neural networks (FNNs)</subject><subject>sequence learning</subject><subject>Task analysis</subject><subject>Trajectory</subject><subject>Writing</subject><issn>2168-2267</issn><issn>2168-2275</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNpdkU1LAzEQhoMoKuoPEEECXrxszcduNjlq8Qtqe7AXTyHNTiS63dVkV7G_3iytPZjLDMkzL8MThE4pGVFK1NV8_HIzYoSREVMyF7nYQYeMCpkxVha7216UB-gkxjeSjkxXSu6jA854IUqhDtHLNZ62X1DjZ6hdNguvpvEr37ziu361-sFT6IOpU-m-2_COuxZPwIQGm6bCT37pLX4wC9_1Zgj47KHpfGrnJr7HY7TnTB3hZFOP0Pzudj5-yCaz-8fx9SSzPFddRnPHOLWq4LkxxkpwRLgScsPlgkIJhJmqAMcWpSsYUdZSx5m0eVVVuWCCH6HLdexHaNMCsdNLHy3UtWmg7aNmXJWiUIXgCb34h761fWjScpoJqgiVnAyBdE3Z0MYYwOmP4Jcm_GhK9GBeD-b1YF5vzKeZ801yv1hCtZ3485yAszXgAWD7rIgcfon_AjuXhkk</recordid><startdate>202201</startdate><enddate>202201</enddate><creator>Salimi-Badr, Armin</creator><creator>Ebadzadeh, Mohammad Mehdi</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>H8D</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0001-6466-5229</orcidid><orcidid>https://orcid.org/0000-0001-6613-7921</orcidid></search><sort><creationdate>202201</creationdate><title>A Novel Self-Organizing Fuzzy Neural Network to Learn and Mimic Habitual Sequential Tasks</title><author>Salimi-Badr, Armin ; Ebadzadeh, Mohammad Mehdi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c349t-14f231c9534aaac8ef06f7e4a38b1e7e02ad5ef2b7f5209cc1f328c4ddd46263</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Algorithms</topic><topic>Artificial neural networks</topic><topic>Fuzzy control</topic><topic>Fuzzy Logic</topic><topic>Fuzzy neural networks</topic><topic>Fuzzy sets</topic><topic>Gradual learning</topic><topic>habits</topic><topic>Learning</topic><topic>multivariate fuzzy sets</topic><topic>Neural networks</topic><topic>Neural Networks, Computer</topic><topic>Neurons</topic><topic>Pattern generation</topic><topic>self-organizing fuzzy neural networks (FNNs)</topic><topic>sequence learning</topic><topic>Task analysis</topic><topic>Trajectory</topic><topic>Writing</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Salimi-Badr, Armin</creatorcontrib><creatorcontrib>Ebadzadeh, Mohammad Mehdi</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE/IET Electronic Library (IEL)</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Mechanical &amp; Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology &amp; Engineering</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE transactions on cybernetics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Salimi-Badr, Armin</au><au>Ebadzadeh, Mohammad Mehdi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Novel Self-Organizing Fuzzy Neural Network to Learn and Mimic Habitual Sequential Tasks</atitle><jtitle>IEEE transactions on cybernetics</jtitle><stitle>TCYB</stitle><addtitle>IEEE Trans Cybern</addtitle><date>2022-01</date><risdate>2022</risdate><volume>52</volume><issue>1</issue><spage>323</spage><epage>332</epage><pages>323-332</pages><issn>2168-2267</issn><eissn>2168-2275</eissn><coden>ITCEB8</coden><abstract>In this article, a new self-organizing fuzzy neural network (FNN) model is presented which is able to simultaneously and accurately learn and reproduce different sequences. Multiple sequence learning is important in performing habitual and skillful tasks, such as writing, signing signatures, and playing piano. Generally, it is indispensable for pattern generation applications. Since multiple sequences have similar parts, local information such as some previous samples is not sufficient to efficiently reproduce them. Instead, it is necessary to consider global and discriminative information, maybe in the very initial samples of each sequence, to first recognize them, and then predict their next sample based on the current local information. Therefore, the structure of the proposed network consists of two parts: 1) sequence identifier, which computes a novel sequence identity value based on initial samples of a sequence, and detects the sequence identity based on proper fuzzy rules and 2) sequence locator , which locates the input sample in the sequence. Therefore, by integrating outputs of these two parts in fuzzy rules, the network is able to produce the proper output based on the current state of each sequence. To learn the proposed structure, a gradual learning procedure is proposed. First, learning is performed by adding new fuzzy rules, based on coverage measure, using available correct data. Next, the initialized parameters are fine-tuned, by the gradient descent algorithm, based on fed back approximated network output as the next input. The proposed method has a dynamic structure able to learn new sequences online. Finally, to investigate the effectiveness of the presented approach, it is used to simultaneously learn and reproduce multiple sequences in different applications, including sequences with similar parts, different patterns, and writing different letters. The performance of the proposed method is evaluated and compared with other existing methods, including the adaptive network-based fuzzy inference system, GDFNN, CFNN, and long short-term memory (LSTM). According to these experiments, the proposed method outperforms traditional FNNs and LSTM in learning multiple sequences.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>32356769</pmid><doi>10.1109/TCYB.2020.2984646</doi><tpages>10</tpages><orcidid>https://orcid.org/0000-0001-6466-5229</orcidid><orcidid>https://orcid.org/0000-0001-6613-7921</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 2168-2267
ispartof IEEE transactions on cybernetics, 2022-01, Vol.52 (1), p.323-332
issn 2168-2267
2168-2275
language eng
recordid cdi_proquest_journals_2619018306
source IEEE Electronic Library (IEL) Journals
subjects Algorithms
Artificial neural networks
Fuzzy control
Fuzzy Logic
Fuzzy neural networks
Fuzzy sets
Gradual learning
habits
Learning
multivariate fuzzy sets
Neural networks
Neural Networks, Computer
Neurons
Pattern generation
self-organizing fuzzy neural networks (FNNs)
sequence learning
Task analysis
Trajectory
Writing
title A Novel Self-Organizing Fuzzy Neural Network to Learn and Mimic Habitual Sequential Tasks
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-13T17%3A39%3A21IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Novel%20Self-Organizing%20Fuzzy%20Neural%20Network%20to%20Learn%20and%20Mimic%20Habitual%20Sequential%20Tasks&rft.jtitle=IEEE%20transactions%20on%20cybernetics&rft.au=Salimi-Badr,%20Armin&rft.date=2022-01&rft.volume=52&rft.issue=1&rft.spage=323&rft.epage=332&rft.pages=323-332&rft.issn=2168-2267&rft.eissn=2168-2275&rft.coden=ITCEB8&rft_id=info:doi/10.1109/TCYB.2020.2984646&rft_dat=%3Cproquest_pubme%3E2619018306%3C/proquest_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c349t-14f231c9534aaac8ef06f7e4a38b1e7e02ad5ef2b7f5209cc1f328c4ddd46263%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2619018306&rft_id=info:pmid/32356769&rft_ieee_id=9082168&rfr_iscdi=true