Autonomous Evolution of Topographic Regularities in Artificial Neural Networks
Looking to nature as inspiration, for at least the past 25 years, researchers in the field of (NE) have developed evolutionary algorithms designed specifically to evolve artificial neural networks (ANNs). Yet the ANNs evolved through NE algorithms lack the distinctive characteristics of biological b...
Saved in:
| Published in | Neural computation Vol. 22; no. 7; pp. 1860 - 1898 |
|---|---|
| Main Authors | , |
| Format | Journal Article |
| Language | English |
| Published |
One Rogers Street, Cambridge, MA 02142-1209, USA
MIT Press
01.07.2010
MIT Press Journals, The |
| Subjects | |
| Online Access | Get full text |
| ISSN | 0899-7667 1530-888X 1530-888X |
| DOI | 10.1162/neco.2010.06-09-1042 |
Cover
| Abstract | Looking to nature as inspiration, for at least the past 25 years, researchers in the field of
(NE) have developed evolutionary algorithms designed specifically to evolve artificial neural networks (ANNs). Yet the ANNs evolved through NE algorithms lack the distinctive characteristics of biological brains, perhaps explaining why NE is not yet a mainstream subject of neural computation. Motivated by this gap, this letter shows that when geometry is introduced to evolved ANNs through the hypercube-based neuroevolution of augmenting topologies algorithm, they begin to acquire characteristics that indeed are reminiscent of biological brains. That is, if the neurons in evolved ANNs are situated at locations in space (i.e., if they are given coordinates), then, as experiments in evolving checkers-playing ANNs in this letter show, topographic maps with symmetries and regularities can evolve spontaneously. The ability to evolve such maps is shown in this letter to provide an important advantage in generalization. In fact, the evolved maps are sufficiently informative that their analysis yields the novel insight that the geometry of the connectivity patterns of more general players is significantly smoother and more contiguous than less general ones. Thus, the results reveal a correlation between generality and smoothness in connectivity patterns. They also hint at the intriguing possibility that as NE matures as a field, its algorithms can evolve ANNs of increasing relevance to those who study neural computation in general. |
|---|---|
| AbstractList | Looking to nature as inspiration, for at least the past 25 years, researchers in the field of
(NE) have developed evolutionary algorithms designed specifically to evolve artificial neural networks (ANNs). Yet the ANNs evolved through NE algorithms lack the distinctive characteristics of biological brains, perhaps explaining why NE is not yet a mainstream subject of neural computation. Motivated by this gap, this letter shows that when geometry is introduced to evolved ANNs through the hypercube-based neuroevolution of augmenting topologies algorithm, they begin to acquire characteristics that indeed are reminiscent of biological brains. That is, if the neurons in evolved ANNs are situated at locations in space (i.e., if they are given coordinates), then, as experiments in evolving checkers-playing ANNs in this letter show, topographic maps with symmetries and regularities can evolve spontaneously. The ability to evolve such maps is shown in this letter to provide an important advantage in generalization. In fact, the evolved maps are sufficiently informative that their analysis yields the novel insight that the geometry of the connectivity patterns of more general players is significantly smoother and more contiguous than less general ones. Thus, the results reveal a correlation between generality and smoothness in connectivity patterns. They also hint at the intriguing possibility that as NE matures as a field, its algorithms can evolve ANNs of increasing relevance to those who study neural computation in general. Looking to nature as inspiration, for at least the past 25 years, researchers in the field of neuroevolution (NE) have developed evolutionary algorithms designed specifically to evolve artificial neural networks (ANNs). Yet the ANNs evolved through NE algorithms lack the distinctive characteristics of biological brains, perhaps explaining why NE is not yet a mainstream subject of neural computation. Motivated by this gap, this letter shows that when geometry is introduced to evolved ANNs through the hypercube-based neuroevolution of augmenting topologies algorithm, they begin to acquire characteristics that indeed are reminiscent of biological brains. That is, if the neurons in evolved ANNs are situated at locations in space (i.e., if they are given coordinates), then, as experiments in evolving checkers-playing ANNs in this letter show, topographic maps with symmetries and regularities can evolve spontaneously. The ability to evolve such maps is shown in this letter to provide an important advantage in generalization. In fact, the evolved maps are sufficiently informative that their analysis yields the novel insight that the geometry of the connectivity patterns of more general players is significantly smoother and more contiguous than less general ones. Thus, the results reveal a correlation between generality and smoothness in connectivity patterns. They also hint at the intriguing possibility that as NE matures as a field, its algorithms can evolve ANNs of increasing relevance to those who study neural computation in general. [PUBLICATION ABSTRACT] Looking to nature as inspiration, for at least the past 25 years, researchers in the field of neuroevolution (NE) have developed evolutionary algorithms designed specifically to evolve artificial neural networks (ANNs). Yet the ANNs evolved through NE algorithms lack the distinctive characteristics of biological brains, perhaps explaining why NE is not yet a mainstream subject of neural computation. Motivated by this gap, this letter shows that when geometry is introduced to evolved ANNs through the hypercube-based neuroevolution of augmenting topologies algorithm, they begin to acquire characteristics that indeed are reminiscent of biological brains. That is, if the neurons in evolved ANNs are situated at locations in space (i.e., if they are given coordinates), then, as experiments in evolving checkers-playing ANNs in this letter show, topographic maps with symmetries and regularities can evolve spontaneously. The ability to evolve such maps is shown in this letter to provide an important advantage in generalization. In fact, the evolved maps are sufficiently informative that their analysis yields the novel insight that the geometry of the connectivity patterns of more general players is significantly smoother and more contiguous than less general ones. Thus, the results reveal a correlation between generality and smoothness in connectivity patterns. They also hint at the intriguing possibility that as NE matures as a field, its algorithms can evolve ANNs of increasing relevance to those who study neural computation in general. Looking to nature as inspiration, for at least the past 25 years, researchers in the field of neuroevolution (NE) have developed evolutionary algorithms designed specifically to evolve artificial neural networks (ANNs). Yet the ANNs evolved through NE algorithms lack the distinctive characteristics of biological brains, perhaps explaining why NE is not yet a mainstream subject of neural computation. Motivated by this gap, this letter shows that when geometry is introduced to evolved ANNs through the hypercube-based neuroevolution of augmenting topologies algorithm, they begin to acquire characteristics that indeed are reminiscent of biological brains. That is, if the neurons in evolved ANNs are situated at locations in space (i.e., if they are given coordinates), then, as experiments in evolving checkers-playing ANNs in this letter show, topographic maps with symmetries and regularities can evolve spontaneously. The ability to evolve such maps is shown in this letter to provide an important advantage in generalization. In fact, the evolved maps are sufficiently informative that their analysis yields the novel insight that the geometry of the connectivity patterns of more general players is significantly smoother and more contiguous than less general ones. Thus, the results reveal a correlation between generality and smoothness in connectivity patterns. They also hint at the intriguing possibility that as NE matures as a field, its algorithms can evolve ANNs of increasing relevance to those who study neural computation in general.Looking to nature as inspiration, for at least the past 25 years, researchers in the field of neuroevolution (NE) have developed evolutionary algorithms designed specifically to evolve artificial neural networks (ANNs). Yet the ANNs evolved through NE algorithms lack the distinctive characteristics of biological brains, perhaps explaining why NE is not yet a mainstream subject of neural computation. Motivated by this gap, this letter shows that when geometry is introduced to evolved ANNs through the hypercube-based neuroevolution of augmenting topologies algorithm, they begin to acquire characteristics that indeed are reminiscent of biological brains. That is, if the neurons in evolved ANNs are situated at locations in space (i.e., if they are given coordinates), then, as experiments in evolving checkers-playing ANNs in this letter show, topographic maps with symmetries and regularities can evolve spontaneously. The ability to evolve such maps is shown in this letter to provide an important advantage in generalization. In fact, the evolved maps are sufficiently informative that their analysis yields the novel insight that the geometry of the connectivity patterns of more general players is significantly smoother and more contiguous than less general ones. Thus, the results reveal a correlation between generality and smoothness in connectivity patterns. They also hint at the intriguing possibility that as NE matures as a field, its algorithms can evolve ANNs of increasing relevance to those who study neural computation in general. |
| Author | Stanley, Kenneth O. Gauci, Jason |
| Author_xml | – sequence: 1 givenname: Jason surname: Gauci fullname: Gauci, Jason email: jgauci@eecs.ucf.edu – sequence: 2 givenname: Kenneth O. surname: Stanley fullname: Stanley, Kenneth O. email: kstanley@eecs.ucf.edu |
| BackLink | http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=22878718$$DView record in Pascal Francis https://www.ncbi.nlm.nih.gov/pubmed/20235822$$D View this record in MEDLINE/PubMed |
| BookMark | eNqFkd1r1UAQxRep2NvqfyASBOlT6uxs9su3S2mtUCpIBd-WzWZTt-Zm425S0b_exHv9oKh9GgZ-5wxnzgHZ62PvCXlK4ZhSgS977-IxwryCKEGXFCp8QFaUMyiVUh_2yAqU1qUUQu6Tg5xvAEBQ4I_IPgIyrhBX5HI9jbGPmzjl4vQ2dtMYYl_EtriKQ7xOdvgYXPHOX0-dTWEMPhehL9ZpDG1wwXbFpZ_SjzF-ielTfkwetrbL_sluHpL3Z6dXJ-flxdvXb07WF6XjQo6lxbYBxkFah6xhjce6Qaw5-NbW3tba2rbxXiiUqDX1DTaqclxJL2uhG8EOydHWd0jx8-TzaDYhO991tvdzFCN5pbQQHO8nGaOg5qfN5PM75E2cUj_HMExwzjXoBXq2g6Z64xszpLCx6av5-dEZeLEDbHa2a5PtXci_OVRSSapmrtpyLsWck29_IRTMUrBZCjZLwQaEAW2WgmfZqzsyF0a7lDYmG7r7xOdb8Sb8EW5BbxGDNAywkmLJQmeXRfYtDP-ygr9Y_ff6d-J80bs |
| CODEN | NEUCEB |
| CitedBy_id | crossref_primary_10_1162_ARTL_a_00150 crossref_primary_10_1016_j_artmed_2013_07_002 crossref_primary_10_1109_LRA_2017_2716418 crossref_primary_10_4236_jilsa_2011_31005 crossref_primary_10_1016_j_ins_2015_03_046 crossref_primary_10_2139_ssrn_4104972 crossref_primary_10_1162_ARTL_a_00071 crossref_primary_10_1007_s12065_012_0086_3 crossref_primary_10_3390_rs13061082 crossref_primary_10_1007_s12065_011_0066_z crossref_primary_10_1007_s12065_020_00500_x crossref_primary_10_1109_ACCESS_2019_2944545 crossref_primary_10_1162_ARTL_a_00185 crossref_primary_10_1038_s41598_017_16548_2 crossref_primary_10_1038_s42256_018_0006_z crossref_primary_10_1016_j_neucom_2018_05_124 crossref_primary_10_1162_artl_a_00301 crossref_primary_10_1109_TCIAIG_2015_2494596 crossref_primary_10_3389_fncom_2017_00112 crossref_primary_10_1371_journal_pcbi_1003399 crossref_primary_10_1016_j_neucom_2017_02_090 crossref_primary_10_1007_s12065_023_00860_0 crossref_primary_10_1109_TNS_2016_2543203 crossref_primary_10_1007_s10462_021_10049_5 crossref_primary_10_1109_TEVC_2010_2104157 crossref_primary_10_1177_1059712313487390 crossref_primary_10_1371_journal_pone_0174635 crossref_primary_10_1016_j_eswa_2016_03_012 crossref_primary_10_3233_HIS_170244 crossref_primary_10_1016_j_neucom_2012_07_010 |
| Cites_doi | 10.1162/106454602320991837 10.1109/3477.499791 10.1007/BF00187293 10.1109/CEC.2002.1004528 10.1162/106365602320169811 10.1162/106454603322221487 10.1007/s10710-007-9028-8 10.1162/106454601317297022 10.1613/jair.368 10.1007/978-3-7091-7533-0_5 10.1016/0004-3702(75)90019-3 10.1109/ICEC.1994.350019 10.1177/105971239200100105 10.1007/s00422-003-0435-5 10.1109/CEC.2001.934446 10.1002/cplx.10047 10.1109/IJCNN.1991.155366 10.1113/jphysiol.1968.sp008455 10.1016/j.nurt.2007.04.009 10.1023/A:1008272615525 10.1016/S1364-6613(99)01440-0 10.1109/ICNN.1993.298673 10.1109/IJCNN.1991.155416 10.1109/TEVC.2005.856210 10.1109/4235.942536 10.1080/095400998116404 10.1109/5.784219 10.1177/105971239400300202 10.1109/JPROC.2004.837633 10.1023/A:1012459627968 10.1073/pnas.90.7.3098 10.1145/1569901.1569995 10.1109/TEVC.2006.886801 10.1109/CEC.2009.4983289 10.1613/jair.1338 10.1006/nimg.1998.0332 10.1007/978-3-540-87700-4_36 10.1038/35023115 10.7551/mitpress/1429.003.0019 10.1162/106454600568834 10.1113/jphysiol.1962.sp006837 10.1177/105971239700500305 10.1146/annurev.neuro.27.070203.144226 10.1016/j.neucom.2005.12.090 10.1007/BF02458823 10.1103/PhysRevLett.102.152001 10.1109/CEC.2002.1004508 10.1162/artl.1994.1.4.353 10.1098/rstb.1952.0012 10.1098/rstb.1977.0050 10.1038/379725a0 10.1145/1569901.1569923 10.1162/artl.2009.15.2.15202 10.1109/72.265960 10.1007/978-0-585-33656-5_3 10.1016/S0893-6080(00)00032-0 10.1007/s12065-007-0002-4 10.1007/978-3-540-24855-2_60 10.1007/PL00007988 10.1093/mind/XCV.379.279 10.1088/0954-898X/7/2/002 10.1007/BF00199581 10.1016/B978-155860783-5/50016-7 10.1145/1276958.1277155 10.1145/1068009.1068340 10.1007/3-540-06867-8_3 |
| ContentType | Journal Article |
| Copyright | 2015 INIST-CNRS Copyright MIT Press Journals Jul 2010 |
| Copyright_xml | – notice: 2015 INIST-CNRS – notice: Copyright MIT Press Journals Jul 2010 |
| DBID | AAYXX CITATION IQODW CGR CUY CVF ECM EIF NPM 7SC 8FD JQ2 L7M L~C L~D 7X8 7TK |
| DOI | 10.1162/neco.2010.06-09-1042 |
| DatabaseName | CrossRef Pascal-Francis Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic Neurosciences Abstracts |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional MEDLINE - Academic Neurosciences Abstracts |
| DatabaseTitleList | Computer and Information Systems Abstracts CrossRef MEDLINE - Academic MEDLINE Neurosciences Abstracts |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science Applied Sciences Mathematics |
| EISSN | 1530-888X |
| EndPage | 1898 |
| ExternalDocumentID | 2051487151 20235822 22878718 10_1162_neco_2010_06_09_1042 neco.2010.06-09-1042.pdf |
| Genre | Journal Article |
| GroupedDBID | --- -~X .4S .DC 0R~ 123 36B 4.4 6IK AAJGR AALMD ABDBF ABDNZ ABIVO ABJNI ABMYL ACGFO ADIYS AEGXH AENEX AFHIN AIAGR ALMA_UNASSIGNED_HOLDINGS ARCSS AVWKF AZFZN BEFXN BFFAM BGNUA BKEBE BPEOZ CAG COF CS3 DU5 EAP EAS EBC EBD EBS ECS EDO EJD EMB EMK EMOBN EPL EPS EST ESX F5P FEDTE FNEHJ HVGLF HZ~ I-F IPLJI JAVBF MCG MINIK MKJ O9- OCL P2P PK0 PQQKQ RMI SV3 TUS WG8 WH7 XJE ZWS 41~ 53G AAFWJ AAYXX ABAZT ABEFU ABVLG ACUHS ACYGS ADMLS AMVHM CITATION H~9 AEILP IQODW AAYOK CGR CUY CVF ECM EIF NPM 7SC 8FD JQ2 L7M L~C L~D 7X8 7TK |
| ID | FETCH-LOGICAL-c567t-a2fd03507ac23d3de2bd22b50efabeab9aafdee68272991ed2d84c587e7b69d63 |
| ISSN | 0899-7667 1530-888X |
| IngestDate | Thu Sep 04 16:17:31 EDT 2025 Fri Sep 05 12:18:47 EDT 2025 Mon Jun 30 06:54:07 EDT 2025 Thu Apr 03 06:55:00 EDT 2025 Mon Jul 21 09:16:58 EDT 2025 Wed Oct 01 02:03:06 EDT 2025 Thu Apr 24 22:59:32 EDT 2025 Mon Mar 11 05:41:05 EDT 2024 Tue Mar 01 17:17:36 EST 2022 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 7 |
| Keywords | Brain Neural computation Correlation Evolutionary algorithm Neural network Topology Topographic map General study Geometry Relevance Neuron Correlation analysis Graph connectivity Experimental design Hypercube |
| Language | English |
| License | CC BY 4.0 |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c567t-a2fd03507ac23d3de2bd22b50efabeab9aafdee68272991ed2d84c587e7b69d63 |
| Notes | July, 2010 ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| PMID | 20235822 |
| PQID | 365559090 |
| PQPubID | 37252 |
| PageCount | 39 |
| ParticipantIDs | mit_journals_necov22i7_302476_2021_11_09_zip_neco_2010_06_09_1042 proquest_journals_365559090 pascalfrancis_primary_22878718 proquest_miscellaneous_754896652 crossref_primary_10_1162_neco_2010_06_09_1042 crossref_citationtrail_10_1162_neco_2010_06_09_1042 proquest_miscellaneous_733108530 pubmed_primary_20235822 mit_journals_10_1162_neco_2010_06_09_1042 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2010-07-01 |
| PublicationDateYYYYMMDD | 2010-07-01 |
| PublicationDate_xml | – month: 07 year: 2010 text: 2010-07-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | One Rogers Street, Cambridge, MA 02142-1209, USA |
| PublicationPlace_xml | – name: One Rogers Street, Cambridge, MA 02142-1209, USA – name: Cambridge, MA – name: United States – name: Cambridge |
| PublicationTitle | Neural computation |
| PublicationTitleAlternate | Neural Comput |
| PublicationYear | 2010 |
| Publisher | MIT Press MIT Press Journals, The |
| Publisher_xml | – name: MIT Press – name: MIT Press Journals, The |
| References | B20 B66 B67 Zhang B.-T. (B97) 1993; 7 B68 Eggenberger P. (B23) 1997 B25 B69 B26 B27 B28 Stanley K. O. (B83) 2002 Miikkulainen R. (B63) 1989 Russell S. (B72) 1995 Whiteson S. (B92) 2003 B70 B71 B73 B30 B31 B75 B32 B33 B77 B35 B79 B38 Gauci J. (B34) 2007 Hubel D. H. (B44) 1988 Gomez F. (B36) 2008; 9 Togelius J. (B89) 2005 B1 B2 B3 Dellaert F. (B22) 1994 B4 Whitley D. (B93) 1995 B5 Taylor M. E. (B88) 2006 B7 B8 Gruau F. (B39) 1996 B9 B80 B81 B82 B84 B41 B85 B42 B86 D'Ambrosio D. B. (B21) 2008 B43 B87 B45 B46 McClelland J. L. (B60) 1986; 1 B47 Bentley P. J. (B10) 1999 B48 B49 Kitano H. (B51) 1990; 4 Bednar J. A. (B6) 2002 Fogel D. (B29) 1992 Harp S. A. (B40) 1989 B90 Montana D. J. (B65) 1989 B91 B94 B95 B52 B96 B54 B11 B55 B12 B56 B13 B57 B14 Goodhill G. J. (B37) 2002; 1 B58 B15 B59 B16 B17 Kohonen T. (B53) 1981 B18 Stanley K. O. (B78) 2005 B19 Kandel E. R. (B50) 2000 McHale G. (B61) 2004 Miller G. F. (B64) 1989 Miikkulainen R. (B62) 2005 Srinivas M. (B76) 1991; 3 Soltoggio A. (B74) 2008 |
| References_xml | – ident: B43 doi: 10.1162/106454602320991837 – volume-title: Computational maps in the visual cortex year: 2005 ident: B62 – ident: B26 doi: 10.1109/3477.499791 – ident: B56 doi: 10.1007/BF00187293 – ident: B11 doi: 10.1109/CEC.2002.1004528 – ident: B84 doi: 10.1162/106365602320169811 – ident: B85 doi: 10.1162/106454603322221487 – ident: B77 doi: 10.1007/s10710-007-9028-8 – start-page: 37 volume-title: Proceedings of the IEEE Symposium on Computational Intelligence and Games year: 2005 ident: B89 – ident: B54 doi: 10.1162/106454601317297022 – ident: B68 doi: 10.1613/jair.368 – ident: B12 doi: 10.1007/978-3-7091-7533-0_5 – volume-title: Eye, brain, and vision year: 1988 ident: B44 – ident: B52 doi: 10.1016/0004-3702(75)90019-3 – start-page: 205 volume-title: Proceedings of the Fourth European Conference on Artificial Life year: 1997 ident: B23 – start-page: 214 volume-title: Proceedings of the 2nd Scandinavian Conference on Image Analysis year: 1981 ident: B53 – ident: B2 doi: 10.1109/ICEC.1994.350019 – ident: B9 doi: 10.1177/105971239200100105 – ident: B15 doi: 10.1007/s00422-003-0435-5 – start-page: 762 volume-title: Proceedings of the 11th International Joint Conference on Artificial Intelligence year: 1989 ident: B65 – ident: B42 doi: 10.1109/CEC.2001.934446 – ident: B75 doi: 10.1002/cplx.10047 – start-page: 347 volume-title: Proceedings of the 1988 Connectionist Models Summer School year: 1989 ident: B63 – start-page: 379 volume-title: Proceedings of the Third International Conference on Genetic Algorithms year: 1989 ident: B64 – year: 2007 ident: B34 publication-title: Proceedings of the Genetic and Evolutionary Computation Conference – volume: 4 start-page: 461 year: 1990 ident: B51 publication-title: Complex Systems – ident: B55 doi: 10.1109/IJCNN.1991.155366 – ident: B46 doi: 10.1113/jphysiol.1968.sp008455 – ident: B71 doi: 10.1016/j.nurt.2007.04.009 – volume-title: Artificial intelligence: A modern approach year: 1995 ident: B72 – ident: B69 doi: 10.1023/A:1008272615525 – ident: B8 doi: 10.1016/S1364-6613(99)01440-0 – start-page: 1321 year: 2006 ident: B88 publication-title: GECCO 2006: Proceedings of the Genetic and Evolutionary Computation Conference – ident: B30 doi: 10.1109/ICNN.1993.298673 – ident: B94 doi: 10.1109/IJCNN.1991.155416 – ident: B79 doi: 10.1109/TEVC.2005.856210 – start-page: 356 volume-title: Proceedings of the Genetic and Evolutionary Computation Conference year: 2003 ident: B92 – ident: B13 doi: 10.1109/4235.942536 – ident: B48 doi: 10.1080/095400998116404 – ident: B96 doi: 10.1109/5.784219 – volume-title: Principles of neural science year: 2000 ident: B50 – volume-title: Proceedings of the Genetic and Evolutionary Computation Conference year: 2002 ident: B83 – ident: B38 doi: 10.1177/105971239400300202 – ident: B33 doi: 10.1109/JPROC.2004.837633 – start-page: 569 year: 2008 ident: B74 publication-title: Artificial Life, 11 – ident: B28 doi: 10.1023/A:1012459627968 – ident: B95 doi: 10.1073/pnas.90.7.3098 – ident: B19 doi: 10.1145/1569901.1569995 – volume-title: Co-evolving body and brain in autonomous agents using a developmental model year: 1994 ident: B22 – ident: B59 doi: 10.1109/TEVC.2006.886801 – ident: B17 doi: 10.1109/CEC.2009.4983289 – ident: B86 doi: 10.1613/jair.1338 – volume: 9 start-page: 937 year: 2008 ident: B36 publication-title: J. Mach. Learn. Res. – start-page: 360 volume-title: Proceedings of the Third International Conference on Genetic Algorithms year: 1989 ident: B40 – ident: B67 doi: 10.1006/nimg.1998.0332 – ident: B18 doi: 10.1007/978-3-540-87700-4_36 – ident: B58 doi: 10.1038/35023115 – start-page: 106 volume-title: Artificial life IX: Proceedings of the Ninth International Conference on the Simulation and Synthesis of Artificial Life year: 2004 ident: B61 doi: 10.7551/mitpress/1429.003.0019 – year: 2008 ident: B21 publication-title: Proceedings of the Genetic and Evolutionary Computation Conference – start-page: 203 volume-title: Genetic algorithms in engineering and computer science year: 1995 ident: B93 – ident: B5 doi: 10.1162/106454600568834 – ident: B45 doi: 10.1113/jphysiol.1962.sp006837 – ident: B35 doi: 10.1177/105971239700500305 – ident: B14 doi: 10.1146/annurev.neuro.27.070203.144226 – ident: B7 doi: 10.1016/j.neucom.2005.12.090 – volume: 1 start-page: 845 volume-title: Encyclopedia of cognitive science year: 2002 ident: B37 – ident: B49 doi: 10.1007/BF02458823 – ident: B1 doi: 10.1103/PhysRevLett.102.152001 – year: 1992 ident: B29 publication-title: Evolving artificial intelligence – ident: B82 doi: 10.1109/CEC.2002.1004508 – ident: B73 doi: 10.1162/artl.1994.1.4.353 – volume: 7 start-page: 199 year: 1993 ident: B97 publication-title: Complex Systems – ident: B90 doi: 10.1098/rstb.1952.0012 – ident: B47 doi: 10.1098/rstb.1977.0050 – ident: B91 doi: 10.1038/379725a0 – ident: B70 doi: 10.1145/1569901.1569923 – start-page: 44–46 year: 2002 ident: B6 publication-title: Neurocomputing – ident: B80 doi: 10.1162/artl.2009.15.2.15202 – ident: B4 doi: 10.1109/72.265960 – start-page: 35 volume-title: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-1999) year: 1999 ident: B10 – start-page: 81 volume-title: Genetic programming 1996: Proceedings of the First Annual Conference year: 1996 ident: B39 – volume: 1 start-page: 3 volume-title: Parallel distributed processing: Explorations in the microstructure of cognition year: 1986 ident: B60 – volume: 3 start-page: 2331 year: 1991 ident: B76 publication-title: IEEE International Joint Conference on Neural Networks – ident: B66 doi: 10.1007/978-0-585-33656-5_3 – volume-title: Proceedings of the IEEE 2005 Symposium on Computational Intelligence and Games year: 2005 ident: B78 – ident: B27 doi: 10.1016/S0893-6080(00)00032-0 – ident: B25 doi: 10.1007/s12065-007-0002-4 – ident: B41 doi: 10.1007/978-3-540-24855-2_60 – ident: B3 doi: 10.1007/PL00007988 – ident: B16 doi: 10.1093/mind/XCV.379.279 – ident: B87 doi: 10.1088/0954-898X/7/2/002 – ident: B32 doi: 10.1007/BF00199581 – ident: B31 doi: 10.1016/B978-155860783-5/50016-7 – ident: B20 doi: 10.1145/1276958.1277155 – ident: B81 doi: 10.1145/1068009.1068340 – ident: B57 doi: 10.1007/3-540-06867-8_3 |
| SSID | ssj0006105 |
| Score | 2.3575628 |
| Snippet | Looking to nature as inspiration, for at least the past 25 years, researchers in the field of
(NE) have developed evolutionary algorithms designed specifically... Looking to nature as inspiration, for at least the past 25 years, researchers in the field of neuroevolution (NE) have developed evolutionary algorithms... |
| SourceID | proquest pubmed pascalfrancis crossref mit |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 1860 |
| SubjectTerms | Algorithms Animals Applied sciences Artificial Intelligence Biological and medical sciences Biological Evolution Combinatorics Combinatorics. Ordered structures Computer science; control theory; systems Computer Simulation - trends Designs and configurations Exact sciences and technology Fundamental and applied biological sciences. Psychology General aspects Humans Learning and adaptive systems Letters Mathematics Mathematics in biology. Statistical analysis. Models. Metrology. Data processing in biology (general aspects) Miscellaneous Nerve Net - physiology Neural networks Neural Networks (Computer) Neurons - physiology Sciences and techniques of general use Topology |
| Title | Autonomous Evolution of Topographic Regularities in Artificial Neural Networks |
| URI | https://direct.mit.edu/neco/article/doi/10.1162/neco.2010.06-09-1042 https://www.ncbi.nlm.nih.gov/pubmed/20235822 https://www.proquest.com/docview/365559090 https://www.proquest.com/docview/733108530 https://www.proquest.com/docview/754896652 |
| Volume | 22 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVEBS databaseName: EBSCOhost Academic Search Ultimate customDbUrl: https://search.ebscohost.com/login.aspx?authtype=ip,shib&custid=s3936755&profile=ehost&defaultdb=asn eissn: 1530-888X dateEnd: 20241003 omitProxy: true ssIdentifier: ssj0006105 issn: 0899-7667 databaseCode: ABDBF dateStart: 19970101 isFulltext: true titleUrlDefault: https://search.ebscohost.com/direct.asp?db=asn providerName: EBSCOhost – providerCode: PRVEBS databaseName: Inspec with Full Text customDbUrl: eissn: 1530-888X dateEnd: 20241003 omitProxy: false ssIdentifier: ssj0006105 issn: 0899-7667 databaseCode: ADMLS dateStart: 19970101 isFulltext: true titleUrlDefault: https://www.ebsco.com/products/research-databases/inspec-full-text providerName: EBSCOhost |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR3LbtswTFjTyy57P7JuhQ67DIO3mI4l-RjsVQxrdlgL5GZIsgwYWJ2gcXro14-05RfWrNsuTmzRoiFSFCnxwdjrPHPS2lwGSS41GiixDXRiIDDa0XoSmVBRNPLpUpycz7-u4lVbq9xHl1Tmnb2-Ma7kf6iKz5CuFCX7D5TtOsUH-B_pi1ekMF7_isaLXUUxCeTF6q48pvrQf71pMlHX-Zmp2PxlnTiVNjeoG581gnJZ1j-1J_h2qKcumyZb13wYHdZ_0TtbNP612_4pFSP2u98-0uft9-GGAp2Fy3ZDwbVCcBagZbwaSkmAATfIgcgLVVMQ4HdZLOrcrmhFew86QX4WaP7BEBxHdHNR04cKucfK4xnnwG6bDtghSCFgwg4XH0-__ejWXFQCYx8YiWjf34SU0j77bkY6yMFFUZFHrN7ipMibaib7zY1a7Th7wO55e4EvGuI_ZHdc-Yjdb2txcC-aH7Nlzwu84wW-zvmAF_iQF3hR8p4XeMMLvOWFJ-z886ezDyeBr5UR2FjIKtCQZ3RILLWFKIsyByYDMPHM5do4bRKtcVo6oQCtqSR0GWRqbmMlnTQiyUT0lE3KdemeM54pnYCTkYqMmoe504C3wmaIQCpj5JRF7eil1ieSp3omP9PaoBSQ0vCnNPwpOU0mKQ3_lAXdW5smkcot8G-QMKmfbdtbYBcjWIK5AihkGqEKKgXCQ4ivE_x1sdnTx_GIBbqPBFC4qIVqyo5anugxRSJGk3yWzKaMd60ooOnUTZcOaZ5SUVS0a6I_gcRzlQgR40c8a5itx-5Z9sXeliN2t5_FL9mkuty5V6goV-bYz5Jfh0m82A |
| linkProvider | EBSCOhost |
| 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=Autonomous+evolution+of+topographic+regularities+in+artificial+neural+networks&rft.jtitle=Neural+computation&rft.au=Gauci%2C+Jason&rft.au=Stanley%2C+Kenneth+O&rft.date=2010-07-01&rft.eissn=1530-888X&rft.volume=22&rft.issue=7&rft.spage=1860&rft_id=info:doi/10.1162%2Fneco.2010.06-09-1042&rft_id=info%3Apmid%2F20235822&rft.externalDocID=20235822 |
| 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 |