Fuzzy neural networks stability in terms of the number of hidden layers

This paper introduces an approach for studying the stability, and generalization capability of one and two hidden layer Fuzzy Flip-Flop based Neural Networks (FNNs) with various fuzzy operators. By employing fuzzy flip-flop neurons as sigmoid function generators, novel function approximators are est...

Full description

Saved in:
Bibliographic Details
Main Authors: Lovassy, R., Koczy, L. T., Gal, L., Rudas, I. J.
Format: Conference Proceeding
Language:English
Subjects:
Artificial neural networks
Biological neural networks
Flip-flops
Function approximation
Fuzzy neural networks
Neurons
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 328
container_issue
container_start_page 323
container_title
container_volume
creator Lovassy, R.
Koczy, L. T.
Gal, L.
Rudas, I. J.
description This paper introduces an approach for studying the stability, and generalization capability of one and two hidden layer Fuzzy Flip-Flop based Neural Networks (FNNs) with various fuzzy operators. By employing fuzzy flip-flop neurons as sigmoid function generators, novel function approximators are established that also avoid overfitting in the case of test data containing noisy items in the form of outliers. It is shown, by comparing with existing standard tansig function based approaches that reducing the network complexity networks with comparable stability are obtained. Finally, examples are given to illustrate the effect of the hidden layer number of neural networks.
doi_str_mv 10.1109/CINTI.2011.6108523
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6108523</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6108523</ieee_id><sourcerecordid>6108523</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-2718ad757e282747b619f5d8fbf566cafda27a1406e37d542aa599876edc237c3</originalsourceid><addsrcrecordid>eNpFj8tKw0AYRkdEUGtfQDfzAolzvywl2FoousnCXZlk_tDRJJWZCZI-vRULfpvD2Rz4ELqnpKSU2Mdq81pvSkYoLRUlRjJ-gW6pkFoTIuT75b8Ieo2WKX2Q05Qy1vIbtF5Nx-OMR5ii60_I34f4mXDKrgl9yDMOI84Qh4QPHc57wOM0NBB_bR-8hxH3boaY7tBV5_oEyzMXqF4919VLsX1bb6qnbREsyQXT1DivpQZmmBa6UdR20puu6aRSreu8Y9pRQRRw7aVgzklrjVbgW8Z1yxfo4S8bAGD3FcPg4rw7_-Y_xfVMlw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Fuzzy neural networks stability in terms of the number of hidden layers</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Lovassy, R. ; Koczy, L. T. ; Gal, L. ; Rudas, I. J.</creator><creatorcontrib>Lovassy, R. ; Koczy, L. T. ; Gal, L. ; Rudas, I. J.</creatorcontrib><description>This paper introduces an approach for studying the stability, and generalization capability of one and two hidden layer Fuzzy Flip-Flop based Neural Networks (FNNs) with various fuzzy operators. By employing fuzzy flip-flop neurons as sigmoid function generators, novel function approximators are established that also avoid overfitting in the case of test data containing noisy items in the form of outliers. It is shown, by comparing with existing standard tansig function based approaches that reducing the network complexity networks with comparable stability are obtained. Finally, examples are given to illustrate the effect of the hidden layer number of neural networks.</description><identifier>ISBN: 1457700441</identifier><identifier>ISBN: 9781457700446</identifier><identifier>EISBN: 145770045X</identifier><identifier>EISBN: 1457700433</identifier><identifier>EISBN: 9781457700453</identifier><identifier>EISBN: 9781457700439</identifier><identifier>DOI: 10.1109/CINTI.2011.6108523</identifier><language>eng</language><publisher>IEEE</publisher><subject>Artificial neural networks ; Biological neural networks ; Flip-flops ; Function approximation ; Fuzzy neural networks ; Neurons</subject><ispartof>2011 IEEE 12th International Symposium on Computational Intelligence and Informatics (CINTI), 2011, p.323-328</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6108523$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6108523$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Lovassy, R.</creatorcontrib><creatorcontrib>Koczy, L. T.</creatorcontrib><creatorcontrib>Gal, L.</creatorcontrib><creatorcontrib>Rudas, I. J.</creatorcontrib><title>Fuzzy neural networks stability in terms of the number of hidden layers</title><title>2011 IEEE 12th International Symposium on Computational Intelligence and Informatics (CINTI)</title><addtitle>CINTI</addtitle><description>This paper introduces an approach for studying the stability, and generalization capability of one and two hidden layer Fuzzy Flip-Flop based Neural Networks (FNNs) with various fuzzy operators. By employing fuzzy flip-flop neurons as sigmoid function generators, novel function approximators are established that also avoid overfitting in the case of test data containing noisy items in the form of outliers. It is shown, by comparing with existing standard tansig function based approaches that reducing the network complexity networks with comparable stability are obtained. Finally, examples are given to illustrate the effect of the hidden layer number of neural networks.</description><subject>Artificial neural networks</subject><subject>Biological neural networks</subject><subject>Flip-flops</subject><subject>Function approximation</subject><subject>Fuzzy neural networks</subject><subject>Neurons</subject><isbn>1457700441</isbn><isbn>9781457700446</isbn><isbn>145770045X</isbn><isbn>1457700433</isbn><isbn>9781457700453</isbn><isbn>9781457700439</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNpFj8tKw0AYRkdEUGtfQDfzAolzvywl2FoousnCXZlk_tDRJJWZCZI-vRULfpvD2Rz4ELqnpKSU2Mdq81pvSkYoLRUlRjJ-gW6pkFoTIuT75b8Ieo2WKX2Q05Qy1vIbtF5Nx-OMR5ii60_I34f4mXDKrgl9yDMOI84Qh4QPHc57wOM0NBB_bR-8hxH3boaY7tBV5_oEyzMXqF4919VLsX1bb6qnbREsyQXT1DivpQZmmBa6UdR20puu6aRSreu8Y9pRQRRw7aVgzklrjVbgW8Z1yxfo4S8bAGD3FcPg4rw7_-Y_xfVMlw</recordid><startdate>201111</startdate><enddate>201111</enddate><creator>Lovassy, R.</creator><creator>Koczy, L. T.</creator><creator>Gal, L.</creator><creator>Rudas, I. J.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201111</creationdate><title>Fuzzy neural networks stability in terms of the number of hidden layers</title><author>Lovassy, R. ; Koczy, L. T. ; Gal, L. ; Rudas, I. J.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-2718ad757e282747b619f5d8fbf566cafda27a1406e37d542aa599876edc237c3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Artificial neural networks</topic><topic>Biological neural networks</topic><topic>Flip-flops</topic><topic>Function approximation</topic><topic>Fuzzy neural networks</topic><topic>Neurons</topic><toplevel>online_resources</toplevel><creatorcontrib>Lovassy, R.</creatorcontrib><creatorcontrib>Koczy, L. T.</creatorcontrib><creatorcontrib>Gal, L.</creatorcontrib><creatorcontrib>Rudas, I. J.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Lovassy, R.</au><au>Koczy, L. T.</au><au>Gal, L.</au><au>Rudas, I. J.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Fuzzy neural networks stability in terms of the number of hidden layers</atitle><btitle>2011 IEEE 12th International Symposium on Computational Intelligence and Informatics (CINTI)</btitle><stitle>CINTI</stitle><date>2011-11</date><risdate>2011</risdate><spage>323</spage><epage>328</epage><pages>323-328</pages><isbn>1457700441</isbn><isbn>9781457700446</isbn><eisbn>145770045X</eisbn><eisbn>1457700433</eisbn><eisbn>9781457700453</eisbn><eisbn>9781457700439</eisbn><abstract>This paper introduces an approach for studying the stability, and generalization capability of one and two hidden layer Fuzzy Flip-Flop based Neural Networks (FNNs) with various fuzzy operators. By employing fuzzy flip-flop neurons as sigmoid function generators, novel function approximators are established that also avoid overfitting in the case of test data containing noisy items in the form of outliers. It is shown, by comparing with existing standard tansig function based approaches that reducing the network complexity networks with comparable stability are obtained. Finally, examples are given to illustrate the effect of the hidden layer number of neural networks.</abstract><pub>IEEE</pub><doi>10.1109/CINTI.2011.6108523</doi><tpages>6</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 1457700441
ispartof 2011 IEEE 12th International Symposium on Computational Intelligence and Informatics (CINTI), 2011, p.323-328
issn
language eng
recordid cdi_ieee_primary_6108523
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Artificial neural networks
Biological neural networks
Flip-flops
Function approximation
Fuzzy neural networks
Neurons
title Fuzzy neural networks stability in terms of the number of hidden layers
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T04%3A38%3A35IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Fuzzy%20neural%20networks%20stability%20in%20terms%20of%20the%20number%20of%20hidden%20layers&rft.btitle=2011%20IEEE%2012th%20International%20Symposium%20on%20Computational%20Intelligence%20and%20Informatics%20(CINTI)&rft.au=Lovassy,%20R.&rft.date=2011-11&rft.spage=323&rft.epage=328&rft.pages=323-328&rft.isbn=1457700441&rft.isbn_list=9781457700446&rft_id=info:doi/10.1109/CINTI.2011.6108523&rft.eisbn=145770045X&rft.eisbn_list=1457700433&rft.eisbn_list=9781457700453&rft.eisbn_list=9781457700439&rft_dat=%3Cieee_6IE%3E6108523%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i90t-2718ad757e282747b619f5d8fbf566cafda27a1406e37d542aa599876edc237c3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6108523&rfr_iscdi=true