Orthogonality of decision boundaries in complex-valued neural networks
This letter presents some results of an analysis on the decision boundaries of complex-valued neural networks whose weights, threshold values, input and output signals are all complex numbers. The main results may be summarized as follows. (1) A decision boundary of a single complex-valued neuron co...
Saved in:
| Published in: | Neural computation Vol. 16; no. 1; p. 73 |
|---|---|
| Main Author: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
United States
01.01.2004
|
| Subjects: | |
| ISSN: | 0899-7667 |
| Online Access: | Get more information |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | This letter presents some results of an analysis on the decision boundaries of complex-valued neural networks whose weights, threshold values, input and output signals are all complex numbers. The main results may be summarized as follows. (1) A decision boundary of a single complex-valued neuron consists of two hypersurfaces that intersect orthogonally, and divides a decision region into four equal sections. The XOR problem and the detection of symmetry problem that cannot be solved with two-layered real-valued neural networks, can be solved by two-layered complex-valued neural networks with the orthogonal decision boundaries, which reveals a potent computational power of complex-valued neural nets. Furthermore, the fading equalization problem can be successfully solved by the two-layered complex-valued neural network with the highest generalization ability. (2) A decision boundary of a three-layered complex-valued neural network has the orthogonal property as a basic structure, and its two hypersurfaces approach orthogonality as all the net inputs to each hidden neuron grow. In particular, most of the decision boundaries in the three-layered complex-valued neural network inetersect orthogonally when the network is trained using Complex-BP algorithm. As a result, the orthogonality of the decision boundaries improves its generalization ability. (3) The average of the learning speed of the Complex-BP is several times faster than that of the Real-BP. The standard deviation of the learning speed of the Complex-BP is smaller than that of the Real-BP. It seems that the complex-valued neural network and the related algorithm are natural for learning complex-valued patterns for the above reasons. |
|---|---|
| AbstractList | This letter presents some results of an analysis on the decision boundaries of complex-valued neural networks whose weights, threshold values, input and output signals are all complex numbers. The main results may be summarized as follows. (1) A decision boundary of a single complex-valued neuron consists of two hypersurfaces that intersect orthogonally, and divides a decision region into four equal sections. The XOR problem and the detection of symmetry problem that cannot be solved with two-layered real-valued neural networks, can be solved by two-layered complex-valued neural networks with the orthogonal decision boundaries, which reveals a potent computational power of complex-valued neural nets. Furthermore, the fading equalization problem can be successfully solved by the two-layered complex-valued neural network with the highest generalization ability. (2) A decision boundary of a three-layered complex-valued neural network has the orthogonal property as a basic structure, and its two hypersurfaces approach orthogonality as all the net inputs to each hidden neuron grow. In particular, most of the decision boundaries in the three-layered complex-valued neural network inetersect orthogonally when the network is trained using Complex-BP algorithm. As a result, the orthogonality of the decision boundaries improves its generalization ability. (3) The average of the learning speed of the Complex-BP is several times faster than that of the Real-BP. The standard deviation of the learning speed of the Complex-BP is smaller than that of the Real-BP. It seems that the complex-valued neural network and the related algorithm are natural for learning complex-valued patterns for the above reasons. This letter presents some results of an analysis on the decision boundaries of complex-valued neural networks whose weights, threshold values, input and output signals are all complex numbers. The main results may be summarized as follows. (1) A decision boundary of a single complex-valued neuron consists of two hypersurfaces that intersect orthogonally, and divides a decision region into four equal sections. The XOR problem and the detection of symmetry problem that cannot be solved with two-layered real-valued neural networks, can be solved by two-layered complex-valued neural networks with the orthogonal decision boundaries, which reveals a potent computational power of complex-valued neural nets. Furthermore, the fading equalization problem can be successfully solved by the two-layered complex-valued neural network with the highest generalization ability. (2) A decision boundary of a three-layered complex-valued neural network has the orthogonal property as a basic structure, and its two hypersurfaces approach orthogonality as all the net inputs to each hidden neuron grow. In particular, most of the decision boundaries in the three-layered complex-valued neural network inetersect orthogonally when the network is trained using Complex-BP algorithm. As a result, the orthogonality of the decision boundaries improves its generalization ability. (3) The average of the learning speed of the Complex-BP is several times faster than that of the Real-BP. The standard deviation of the learning speed of the Complex-BP is smaller than that of the Real-BP. It seems that the complex-valued neural network and the related algorithm are natural for learning complex-valued patterns for the above reasons.This letter presents some results of an analysis on the decision boundaries of complex-valued neural networks whose weights, threshold values, input and output signals are all complex numbers. The main results may be summarized as follows. (1) A decision boundary of a single complex-valued neuron consists of two hypersurfaces that intersect orthogonally, and divides a decision region into four equal sections. The XOR problem and the detection of symmetry problem that cannot be solved with two-layered real-valued neural networks, can be solved by two-layered complex-valued neural networks with the orthogonal decision boundaries, which reveals a potent computational power of complex-valued neural nets. Furthermore, the fading equalization problem can be successfully solved by the two-layered complex-valued neural network with the highest generalization ability. (2) A decision boundary of a three-layered complex-valued neural network has the orthogonal property as a basic structure, and its two hypersurfaces approach orthogonality as all the net inputs to each hidden neuron grow. In particular, most of the decision boundaries in the three-layered complex-valued neural network inetersect orthogonally when the network is trained using Complex-BP algorithm. As a result, the orthogonality of the decision boundaries improves its generalization ability. (3) The average of the learning speed of the Complex-BP is several times faster than that of the Real-BP. The standard deviation of the learning speed of the Complex-BP is smaller than that of the Real-BP. It seems that the complex-valued neural network and the related algorithm are natural for learning complex-valued patterns for the above reasons. |
| Author | Nitta, Tohru |
| Author_xml | – sequence: 1 givenname: Tohru surname: Nitta fullname: Nitta, Tohru email: tohru-nitta@aist.go.jp organization: National Institute of Advanced Industrial Science and Technology, Tsukuba-shi, Ibaraki, Japan. tohru-nitta@aist.go.jp |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/15006024$$D View this record in MEDLINE/PubMed |
| BookMark | eNo1jz1PwzAYhD0U0Q_4ASwoE1vgdezY8YgqCkiVusAc-RMMiV3sBOi_J4gyPae700m3RLMQg0XoAsM1xqy6gUYIzhhQBpxQADxDi1-vnEw-R8uc3wCAYahP0RzXk4SKLtBml4bX-BKD7PxwKKIrjNU--xgKFcdgZPI2Fz4UOvb7zn6Xn7IbrSmCHZPsJgxfMb3nM3TiZJft-ZEr9Ly5e1o_lNvd_eP6dlvquqJDSShprGoUCCKpE0bUzEnmKqk14Q2pG0Udw67hBMA5rQwmwKeYKCpMLUy1Qld_u_sUP0abh7b3Wduuk8HGMbcccywwwVPx8lgcVW9Nu0--l-nQ_j-vfgDKJFuT |
| CitedBy_id | crossref_primary_10_1016_j_neunet_2016_08_008 crossref_primary_10_1007_s00521_024_09917_2 crossref_primary_10_1016_j_neucom_2012_03_003 crossref_primary_10_1186_s12859_016_1209_0 crossref_primary_10_1016_j_artint_2023_103951 crossref_primary_10_1016_j_cmpb_2018_07_015 crossref_primary_10_1109_TCYB_2022_3194059 crossref_primary_10_1109_TSMC_2024_3371164 crossref_primary_10_1007_s13042_012_0112_x crossref_primary_10_1007_s11571_014_9312_2 crossref_primary_10_1109_TNNLS_2015_2494361 crossref_primary_10_1016_j_cnsns_2022_106581 crossref_primary_10_1007_s11063_016_9563_5 crossref_primary_10_1038_s41467_020_20719_7 crossref_primary_10_1186_s13662_017_1266_3 crossref_primary_10_1016_j_neucom_2013_04_040 crossref_primary_10_1016_j_chaos_2015_08_003 crossref_primary_10_3390_physics3040058 crossref_primary_10_1007_s00521_015_2142_2 crossref_primary_10_1007_s00500_018_3216_8 crossref_primary_10_1016_j_neucom_2023_126358 crossref_primary_10_1109_TSMC_2018_2836952 crossref_primary_10_1080_00207721_2019_1623340 crossref_primary_10_1016_j_eswa_2023_121166 crossref_primary_10_1016_j_neunet_2016_01_007 crossref_primary_10_1155_2009_329173 crossref_primary_10_1002_mma_4434 crossref_primary_10_1007_s13369_020_04692_3 crossref_primary_10_1002_nbm_4312 crossref_primary_10_1016_j_jmgm_2017_07_015 crossref_primary_10_1007_s12190_025_02485_1 crossref_primary_10_1016_j_neunet_2019_09_032 crossref_primary_10_1049_el_2014_3572 crossref_primary_10_3390_math12213345 crossref_primary_10_1016_j_amc_2016_11_027 crossref_primary_10_1016_j_asoc_2024_112682 crossref_primary_10_1109_TBCAS_2017_2719631 crossref_primary_10_1007_s00521_017_3030_8 crossref_primary_10_1186_s13660_017_1490_0 crossref_primary_10_1016_j_amc_2016_08_054 crossref_primary_10_1162_NECO_a_00254 crossref_primary_10_1063_5_0254013 crossref_primary_10_1007_s12200_022_00009_4 crossref_primary_10_1109_JAS_2022_105743 crossref_primary_10_1016_j_neucom_2018_05_074 crossref_primary_10_1016_j_neunet_2015_03_007 crossref_primary_10_1109_TNNLS_2017_2677446 crossref_primary_10_1016_j_neunet_2016_05_003 crossref_primary_10_1007_s11063_017_9626_2 crossref_primary_10_1155_2010_829692 crossref_primary_10_1155_2014_263847 crossref_primary_10_1109_TSMC_2021_3055501 crossref_primary_10_1016_j_neunet_2013_02_002 crossref_primary_10_1109_TNNLS_2018_2801297 crossref_primary_10_1155_2014_397532 crossref_primary_10_1109_TNNLS_2014_2321420 crossref_primary_10_1155_2021_5577675 crossref_primary_10_3390_nano12132171 crossref_primary_10_3390_a17080361 crossref_primary_10_1109_TNNLS_2021_3105901 crossref_primary_10_1007_s11063_013_9305_x crossref_primary_10_1016_j_jag_2025_104418 crossref_primary_10_1016_j_ins_2014_07_042 crossref_primary_10_1016_j_neunet_2012_02_015 crossref_primary_10_1587_nolta_14_175 crossref_primary_10_1016_j_amc_2017_05_021 crossref_primary_10_1007_s11063_017_9736_x crossref_primary_10_1109_TNNLS_2021_3129269 crossref_primary_10_1016_j_engappai_2024_108352 crossref_primary_10_1109_TNNLS_2019_2933882 crossref_primary_10_1111_jerd_13079 crossref_primary_10_1109_ACCESS_2020_3025373 crossref_primary_10_1109_TNNLS_2012_2235460 crossref_primary_10_3390_math11183845 crossref_primary_10_1109_TCYB_2019_2946703 crossref_primary_10_1016_j_neunet_2016_10_010 crossref_primary_10_1016_j_neucom_2013_06_009 crossref_primary_10_1016_j_neucom_2014_08_015 crossref_primary_10_1007_s11571_025_10306_1 crossref_primary_10_1016_j_neucom_2015_10_120 crossref_primary_10_1109_ACCESS_2021_3076345 crossref_primary_10_1109_ACCESS_2015_2506601 crossref_primary_10_1016_j_neucom_2022_11_079 crossref_primary_10_1109_TNNLS_2020_2984267 crossref_primary_10_1007_s12555_018_0679_4 crossref_primary_10_1016_j_neunet_2021_01_014 crossref_primary_10_1109_TNNLS_2017_2704286 crossref_primary_10_1007_s11431_017_9284_y crossref_primary_10_1016_j_neucom_2014_04_075 crossref_primary_10_1007_s11063_018_9805_9 crossref_primary_10_1007_s11071_014_1628_2 crossref_primary_10_1109_JBHI_2014_2387795 crossref_primary_10_1162_0899766053429381 crossref_primary_10_1016_j_neucom_2022_04_010 crossref_primary_10_1016_j_neucom_2025_129412 crossref_primary_10_1186_s13662_018_1666_z crossref_primary_10_3390_math11102275 crossref_primary_10_17721_1812_5409_2025_1_12 crossref_primary_10_1016_j_neunet_2017_03_006 crossref_primary_10_1007_s11063_018_9790_z crossref_primary_10_1260_2040_2295_6_3_281 crossref_primary_10_1007_s00521_016_2305_9 crossref_primary_10_1515_bmt_2016_0156 crossref_primary_10_1016_j_asoc_2015_04_022 crossref_primary_10_1109_TNNLS_2021_3070966 crossref_primary_10_1007_s11063_017_9692_5 crossref_primary_10_1007_s00521_018_3920_4 crossref_primary_10_1109_TNNLS_2020_2966031 crossref_primary_10_1155_2022_5759152 crossref_primary_10_1016_j_ins_2011_11_003 crossref_primary_10_1007_s00521_021_06555_w crossref_primary_10_1186_s13662_018_1521_2 |
| ContentType | Journal Article |
| DBID | CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1162/08997660460734001 |
| 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 | Computer Science |
| ExternalDocumentID | 15006024 |
| Genre | Journal Article |
| GroupedDBID | --- -~X .4S .DC 0R~ 123 36B 4.4 41~ 53G 6IK AAJGR AALMD AAYOK ABAZT ABDBF ABDNZ ABEFU ABIVO ABJNI ACGFO ACUHS ACYGS ADIYS ADMLS AEGXH AEILP AENEX AFHIN AIAGR ALMA_UNASSIGNED_HOLDINGS ARCSS AVWKF AZFZN BEFXN BFFAM BGNUA BKEBE BPEOZ CAG CGR COF CS3 CUY CVF DU5 EAP EAS EBC EBD EBS ECM ECS EDO EIF EJD EMB EMK EMOBN EPL EPS EST ESX F5P FEDTE FNEHJ HVGLF HZ~ H~9 I-F IPLJI JAVBF MCG MINIK MKJ NPM O9- OCL P2P PK0 PQQKQ RMI SV3 TUS WG8 WH7 XJE ZWS 7X8 ABUFD ABVLG AMVHM |
| ID | FETCH-LOGICAL-c524t-3438eb8b093a4f9d956fa6f2acc378358b4f61f87300ffcbd1307f2a3b49d59d2 |
| IEDL.DBID | 7X8 |
| ISICitedReferencesCount | 146 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000187146600004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0899-7667 |
| IngestDate | Sun Nov 09 10:57:00 EST 2025 Wed Feb 19 01:36:42 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c524t-3438eb8b093a4f9d956fa6f2acc378358b4f61f87300ffcbd1307f2a3b49d59d2 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PMID | 15006024 |
| PQID | 71719131 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_71719131 pubmed_primary_15006024 |
| PublicationCentury | 2000 |
| PublicationDate | 2004-Jan 20040101 |
| PublicationDateYYYYMMDD | 2004-01-01 |
| PublicationDate_xml | – month: 01 year: 2004 text: 2004-Jan |
| PublicationDecade | 2000 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Neural computation |
| PublicationTitleAlternate | Neural Comput |
| PublicationYear | 2004 |
| SSID | ssj0006105 |
| Score | 2.182368 |
| Snippet | This letter presents some results of an analysis on the decision boundaries of complex-valued neural networks whose weights, threshold values, input and output... |
| SourceID | proquest pubmed |
| SourceType | Aggregation Database Index Database |
| StartPage | 73 |
| SubjectTerms | Algorithms Artificial Intelligence Decision Support Techniques Neural Networks (Computer) |
| Title | Orthogonality of decision boundaries in complex-valued neural networks |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/15006024 https://www.proquest.com/docview/71719131 |
| Volume | 16 |
| WOSCitedRecordID | wos000187146600004&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/eLvHCXMwpV07T8MwELYKZWChvClPD6xW69h1HAkJIUTFAKUDSN0qP2LokpS2IH4-d4kjJsTAksFRrOhytr_v7nIfIZfeBqO9DEzagWYy055pqzkL2iXK9l0wtWrJQzoa6ckkG7fIVfMvDJZVNntitVH70mGMvAe0A6iF4Nfzd4aaUZhbjQIaa6QtAMigT6eTn17hKhYwAqNgqVJpzGlylfRwDIYwKZgK8GL-O76szplh539vuE22Ir6kN7VD7JBWXuySTqPdQONS3iPDp8XqrXyNOJyWgfqotkNtpbSEFJrOClrVnOdfDLuC555i_0uYv6irx5f75GV493x7z6KmAnODRK6YkELnVtt-JowMmQd6FIwKiXFOYBBIWxkUDxrb2IfgrIczLoXbwsrMDzKfHJD1oizyI0KNzEwiDecOWRl8Vewc7wCA5dwLmKFLLho7TcFnMRFhirz8WE4bS3XJYW3q6bxurTEFeNpXABuO_3z2hGzWRTQYDTkl7QCrNT8jG-5zNVsuzitXgOto_PgNlQu-sg |
| 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=Orthogonality+of+decision+boundaries+in+complex-valued+neural+networks&rft.jtitle=Neural+computation&rft.au=Nitta%2C+Tohru&rft.date=2004-01-01&rft.issn=0899-7667&rft.volume=16&rft.issue=1&rft.spage=73&rft_id=info:doi/10.1162%2F08997660460734001&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0899-7667&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0899-7667&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0899-7667&client=summon |