Exploring the Relationship Between Topology and Function in Evolved Neural Networks

Understanding the relationship between structure and function in neural networks is essential to explaining their operation. Greater awareness of the link between topology and application could lead to wider adoption, particularly in mission-critical systems. Here, we examine and analyze the topolog...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2020 IEEE Symposium Series on Computational Intelligence (SSCI) S. 2304 - 2311
Hauptverfasser: Showalter, Ian, Schwartz, Howard
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.12.2020
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Understanding the relationship between structure and function in neural networks is essential to explaining their operation. Greater awareness of the link between topology and application could lead to wider adoption, particularly in mission-critical systems. Here, we examine and analyze the topology of very small, minimally sized neurocontrollers that have been evolved for an extended number of generations. Previously demonstrated Lamarckian-inherited neuromodulated evolutionary neurocontrollers are synthesized to operate a simulated vehicle pursuing a basic evader vehicle in the pursuit-evasion game. Both vehicles are subject to the effects of mass and drag. Constraints in the number of neurons and synapses are used to control network size. Additional objectives are added to the multiobjective optimization algorithm to encourage the selection of neural networks with the fewest neurons and synapses. It is shown that patterns emerge in the neuromodulatory neurons, in the direct connections between neurocontroller inputs and outputs, and that topologies similar to those used in classical control are evolved. Additionally, a neurocontroller constructed from the most commonly occurring neurons that successfully capture the evader is demonstrated.
AbstractList Understanding the relationship between structure and function in neural networks is essential to explaining their operation. Greater awareness of the link between topology and application could lead to wider adoption, particularly in mission-critical systems. Here, we examine and analyze the topology of very small, minimally sized neurocontrollers that have been evolved for an extended number of generations. Previously demonstrated Lamarckian-inherited neuromodulated evolutionary neurocontrollers are synthesized to operate a simulated vehicle pursuing a basic evader vehicle in the pursuit-evasion game. Both vehicles are subject to the effects of mass and drag. Constraints in the number of neurons and synapses are used to control network size. Additional objectives are added to the multiobjective optimization algorithm to encourage the selection of neural networks with the fewest neurons and synapses. It is shown that patterns emerge in the neuromodulatory neurons, in the direct connections between neurocontroller inputs and outputs, and that topologies similar to those used in classical control are evolved. Additionally, a neurocontroller constructed from the most commonly occurring neurons that successfully capture the evader is demonstrated.
Author Showalter, Ian
Schwartz, Howard
Author_xml – sequence: 1
  givenname: Ian
  surname: Showalter
  fullname: Showalter, Ian
  email: ianshowalter@cmail.carleton.ca
  organization: Carleton University,Department of Systems and Computer Engineering,Ottawa,Canada
– sequence: 2
  givenname: Howard
  surname: Schwartz
  fullname: Schwartz, Howard
  email: Howard.Schwartz@sce.carleton.ca
  organization: Carleton University,Department of Systems and Computer Engineering,Ottawa,Canada
BookMark eNotz91KwzAYxvEIeqBzVyBIbqA1X8vHoZbODYaCnccjbd5uwZiUttvc3TtxR7-TPw88d-g6pggIPVKSU0rMU1UVS6E04TkjjOSGE02NvEJTozRVTFM2E4rfoqr86ULqfdzicQf4A4IdfYrDznf4BcYjQMTr1KWQtidso8PzfWz-CuwjLg8pHMDhN9j3NpwZj6n_Gu7RTWvDANOLE_Q5L9fFIlu9vy6L51XmGeFjRlvSKNDOzqTgTgKrWyEa20oOFAShUjbMnHG1E0woqQ0V1lkLtKa6FjWfoIf_XQ8Am67337Y_bS5X-S_W8E9A
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/SSCI47803.2020.9308196
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781728125473
1728125472
EndPage 2311
ExternalDocumentID 9308196
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i203t-1f0c7e8da5643d6e2bf44caf63e1e40166c29016dbd424768914adaae1b18b4b3
IEDL.DBID RIE
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000682772902047&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Thu Jun 29 18:38:05 EDT 2023
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-1f0c7e8da5643d6e2bf44caf63e1e40166c29016dbd424768914adaae1b18b4b3
PageCount 8
ParticipantIDs ieee_primary_9308196
PublicationCentury 2000
PublicationDate 2020-Dec.-1
PublicationDateYYYYMMDD 2020-12-01
PublicationDate_xml – month: 12
  year: 2020
  text: 2020-Dec.-1
  day: 01
PublicationDecade 2020
PublicationTitle 2020 IEEE Symposium Series on Computational Intelligence (SSCI)
PublicationTitleAbbrev SSCI
PublicationYear 2020
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.755592
Snippet Understanding the relationship between structure and function in neural networks is essential to explaining their operation. Greater awareness of the link...
SourceID ieee
SourceType Publisher
StartPage 2304
SubjectTerms Artificial Neural Network
Autonomous Vehicle
Biological neural networks
Complexity theory
Evolutionary computation
Games
Hebbian Learning
Lamarckian Inheritance
Multiobjective
Network topology
Neurocontrollers
Neuroevolution
Neuromodulation
Pursuit-Evasion
Topology
Unsupervised Learning
Title Exploring the Relationship Between Topology and Function in Evolved Neural Networks
URI https://ieeexplore.ieee.org/document/9308196
WOSCitedRecordID wos000682772902047&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1La8MwDBZt2WGnbbRjb3zYcWnjxPXjutKywSiFdtBb8UNhgZGWvmD_fnYSMga77GRjBAYJLMn6PgngUaeJcFkiImqE9QmKUZEJBUfpuJKaSct02TL_TUyncrlUsxY8NVwYRCzBZ9gP27KW79b2EL7KBioNDoy3oS0Er7haNemXxmown49emZBx6rO-JO7Xwr-mppROY3L2v-vOoffDviOzxq9cQAuLLswbsBzxIRtpMGwf-YY8V1grsqgGHnwRXTgy8Q4rSJC8IGP_Bh3RkdCJQ3_6pYR-73rwPhkvRi9RPRAhypM43Uc0i61A6fTQxxGOY2IyxqzOeIoUfaLEuQ1lUe6MYwnziYSiTDutkRoqDTPpJXSKdYFXQHgmFaZCCI0-pjBWGzccertRKnScobqGblDIalP1vFjVurj5-_gWToPOK5jHHXT22wPew4k97vPd9qE01DfBX5ch
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA61CnpSacW3OXh0281uNo-r0tJiLYVW6K3kMYsLsi19gf_eZHdZEbx4SggDgRnIzGS-bwahRxVH3KYRD4jmxiUoWgbaFxyFZVIoKgxVRcv8ER-PxXwuJw30VHNhAKAAn0HHb4tavl2anf8q68rYOzB2gA4TSqOwZGtVtF8Syu50-jKkXISxy_uisFOJ_5qbUriN_un_LjxD7R_-HZ7UnuUcNSBvoWkNl8MuaMM1iu0jW-HnEm2FZ-XIgy-scov7zmV5CZzluOdeoT1Y7HtxqE-3FODvTRu993uzl0FQjUQIsiiMtwFJQ8NBWJW4SMIyiHRKqVEpi4GAS5UYM74wyqy2NKIulZCEKqsUEE2Epjq-QM18mcMlwiwVEmLOuQIXVWijtE0SZzlCuApTkFeo5RWyWJVdLxaVLq7_Pn5Ax4PZ22gxGo5fb9CJ138J-rhFze16B3foyOy32WZ9XxjtG8v0mmg
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%3Abook&rft.genre=proceeding&rft.title=2020+IEEE+Symposium+Series+on+Computational+Intelligence+%28SSCI%29&rft.atitle=Exploring+the+Relationship+Between+Topology+and+Function+in+Evolved+Neural+Networks&rft.au=Showalter%2C+Ian&rft.au=Schwartz%2C+Howard&rft.date=2020-12-01&rft.pub=IEEE&rft.spage=2304&rft.epage=2311&rft_id=info:doi/10.1109%2FSSCI47803.2020.9308196&rft.externalDocID=9308196