A modified error backpropagation algorithm for complex-value neural networks

The complex-valued backpropagation algorithm has been widely used in fields of dealing with telecommunications, speech recognition and image processing with Fourier transformation. However, the local minima problem usually occurs in the process of learning. To solve this problem and to speed up the...

Full description

Saved in:
Bibliographic Details
Published in:International journal of neural systems Vol. 15; no. 6; p. 435
Main Authors: Chen, Xiaoming, Tang, Zheng, Variappan, Catherine, Li, Songsong, Okada, Toshimi
Format: Journal Article
Language:English
Published: Singapore 01.12.2005
Subjects:
Algorithms
Artificial Intelligence
Computer Simulation
Learning
Mathematics
Neural Networks (Computer)
Signal Processing, Computer-Assisted
ISSN:0129-0657
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The complex-valued backpropagation algorithm has been widely used in fields of dealing with telecommunications, speech recognition and image processing with Fourier transformation. However, the local minima problem usually occurs in the process of learning. To solve this problem and to speed up the learning process, we propose a modified error function by adding a term to the conventional error function, which is corresponding to the hidden layer error. The simulation results show that the proposed algorithm is capable of preventing the learning from sticking into the local minima and of speeding up the learning.
AbstractList The complex-valued backpropagation algorithm has been widely used in fields of dealing with telecommunications, speech recognition and image processing with Fourier transformation. However, the local minima problem usually occurs in the process of learning. To solve this problem and to speed up the learning process, we propose a modified error function by adding a term to the conventional error function, which is corresponding to the hidden layer error. The simulation results show that the proposed algorithm is capable of preventing the learning from sticking into the local minima and of speeding up the learning.
The complex-valued backpropagation algorithm has been widely used in fields of dealing with telecommunications, speech recognition and image processing with Fourier transformation. However, the local minima problem usually occurs in the process of learning. To solve this problem and to speed up the learning process, we propose a modified error function by adding a term to the conventional error function, which is corresponding to the hidden layer error. The simulation results show that the proposed algorithm is capable of preventing the learning from sticking into the local minima and of speeding up the learning.The complex-valued backpropagation algorithm has been widely used in fields of dealing with telecommunications, speech recognition and image processing with Fourier transformation. However, the local minima problem usually occurs in the process of learning. To solve this problem and to speed up the learning process, we propose a modified error function by adding a term to the conventional error function, which is corresponding to the hidden layer error. The simulation results show that the proposed algorithm is capable of preventing the learning from sticking into the local minima and of speeding up the learning.
Author Li, Songsong
Variappan, Catherine
Okada, Toshimi
Tang, Zheng
Chen, Xiaoming
Author_xml – sequence: 1
  givenname: Xiaoming
  surname: Chen
  fullname: Chen, Xiaoming
  email: xmchen1@hotmail.com
  organization: Faculty of Engineering, Toyama University, 3190 Gofuku, Toyama-shi, Toyama 930-8555, Japan. xmchen1@hotmail.com
– sequence: 2
  givenname: Zheng
  surname: Tang
  fullname: Tang, Zheng
– sequence: 3
  givenname: Catherine
  surname: Variappan
  fullname: Variappan, Catherine
– sequence: 4
  givenname: Songsong
  surname: Li
  fullname: Li, Songsong
– sequence: 5
  givenname: Toshimi
  surname: Okada
  fullname: Okada, Toshimi
BackLink https://www.ncbi.nlm.nih.gov/pubmed/16385633$$D View this record in MEDLINE/PubMed
BookMark eNo1j0lPwzAUhH0oogv8AC4oJ26B57X2sarYpEpc4Bw5zksJdeJgJyz_niDKaaSZT6OZJZl1oUNCLihcUyrYTQLKDCi5BgkAgqkZWfxa-a83J8uU3gCoWAt9SuZUcS0V5wuy22RtqJq6wSrDGEPMSusOfQy93duhCV1m_T7EZnhts3pKXWh7j1_5h_UjZh2O0fpJhs8QD-mMnNTWJzw_6oq83N0-bx_y3dP943azy50ApXLL7ForRMV0ZWWplBO109M6KTiloB2yinNDrWGWKzSm1LIsa-a0q1xtBFuRq7_eaef7iGko2iY59N52GMZUKANCAcgJvDyCY9liVfSxaW38Lv7_sx8sa12h
CitedBy_id crossref_primary_10_1260_2040_2295_6_3_281
crossref_primary_10_1007_s13369_020_04692_3
crossref_primary_10_1016_j_artmed_2007_02_001
crossref_primary_10_1016_j_cam_2011_05_048
crossref_primary_10_1109_TNNLS_2021_3105901
crossref_primary_10_1007_s10916_008_9142_z
ContentType Journal Article
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1142/s0129065705000426
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Mathematics
Computer Science
ExternalDocumentID 16385633
Genre Journal Article
GroupedDBID ---
.DC
0R~
36B
4.4
53G
5GY
ADSJI
AENEX
ALMA_UNASSIGNED_HOLDINGS
CAG
CGR
COF
CS3
CUY
CVF
DU5
EBS
ECM
EIF
EJD
EMOBN
ESX
F5P
HZ~
NPM
O9-
P2P
P71
RWJ
WSC
7X8
ID FETCH-LOGICAL-c4066-a2a786ee628da5b66c4fc80015431108ce2d3391a92a36e99b85bbf2c8cdcf942
IEDL.DBID 7X8
ISICitedReferencesCount 14
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000234235100003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0129-0657
IngestDate Fri Jul 11 10:47:56 EDT 2025
Sat Sep 28 07:52:46 EDT 2024
IsPeerReviewed true
IsScholarly true
Issue 6
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c4066-a2a786ee628da5b66c4fc80015431108ce2d3391a92a36e99b85bbf2c8cdcf942
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 16385633
PQID 69046005
PQPubID 23479
ParticipantIDs proquest_miscellaneous_69046005
pubmed_primary_16385633
PublicationCentury 2000
PublicationDate 2005-Dec
20051201
PublicationDateYYYYMMDD 2005-12-01
PublicationDate_xml – month: 12
  year: 2005
  text: 2005-Dec
PublicationDecade 2000
PublicationPlace Singapore
PublicationPlace_xml – name: Singapore
PublicationTitle International journal of neural systems
PublicationTitleAlternate Int J Neural Syst
PublicationYear 2005
SSID ssj0014748
Score 1.7760602
Snippet The complex-valued backpropagation algorithm has been widely used in fields of dealing with telecommunications, speech recognition and image processing with...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 435
SubjectTerms Algorithms
Artificial Intelligence
Computer Simulation
Learning
Mathematics
Neural Networks (Computer)
Signal Processing, Computer-Assisted
Title A modified error backpropagation algorithm for complex-value neural networks
URI https://www.ncbi.nlm.nih.gov/pubmed/16385633
https://www.proquest.com/docview/69046005
Volume 15
WOSCitedRecordID wos000234235100003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T8MwELYKZWChvClPD6xWVduxHQkJVYiKAapKgNStcvwABE1KWhA_n7OTiAkxsGRLbF3u8fnufB9C595ATDZJP3g_OKAwrol2zhPLDTeCcmmpiWQTcjRSk0k6bqGL5i5MaKtsfGJ01LYwIUfeg1Mch-CcXM7fSeCMCrXVmkBjBbUZAJlglnLyU0PgMnJnhUwLgUAr65pmn9PefUy_hK6PwAfAqfgdX8Y4M-z8b4ebaKPGl3hQKcQWarl8G3Ua7gZcm_IOuh3gWWFfPCBQ7MqyKHGmzSusCA4m_iys357g-8vnGQZci2PrufsiYTi4w2EKJqySVz3ki130OLx-uLohNbMCMRDABdFUSyWcE1RZnWRCGO6NiniKhXsBxlHLQKI6pZoJl6aZSrLMU6OMNT7ldA-t5kXuDhBWWmoHMEMIr7iyMlNOhoHfDHCAY1Z30VkjrSlobihH6NwVH4tpI68u2q8EPp1XAzamASMmgrHDP989QuvVLNXQX3KM2h5s1p2gNfO5fFmUp1Eh4Dka330DAj3AcQ
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+modified+error+backpropagation+algorithm+for+complex-value+neural+networks&rft.jtitle=International+journal+of+neural+systems&rft.au=Chen%2C+Xiaoming&rft.au=Tang%2C+Zheng&rft.au=Variappan%2C+Catherine&rft.au=Li%2C+Songsong&rft.date=2005-12-01&rft.issn=0129-0657&rft.volume=15&rft.issue=6&rft.spage=435&rft_id=info:doi/10.1142%2Fs0129065705000426&rft_id=info%3Apmid%2F16385633&rft_id=info%3Apmid%2F16385633&rft.externalDocID=16385633
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0129-0657&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0129-0657&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0129-0657&client=summon