Computing Based on Material Training: Application to Binary Classification Problems

Evolution-in-materio is a form of unconventional computing combining materials' training and evolutionary search algorithms. In previous work, a mixture of single-walled-carbon-nanotubes (SWCNTs) dispersed in a liquid crystal (LC) was trained so that its morphology and electrical properties wer...

Full description

Saved in:
Bibliographic Details
Published in:2017 IEEE International Conference on Rebooting Computing (ICRC) pp. 1 - 8
Main Authors: Vissol-Gaudin, E., Kotsialos, A., Groves, C., Pearson, C., Zeze, D. A., Petty, M. C.
Format: Conference Proceeding
Language:English
Published: IEEE 01.11.2017
Subjects:
Complexity theory
Current measurement
Hardware
Liquids
Nanotubes
Optimization
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Evolution-in-materio is a form of unconventional computing combining materials' training and evolutionary search algorithms. In previous work, a mixture of single-walled-carbon-nanotubes (SWCNTs) dispersed in a liquid crystal (LC) was trained so that its morphology and electrical properties were gradually changed to perform a computational task. Material-based computation is treated as an optimisation problem with a hybrid search space consisting of the voltages used for creating the electrical field and the material's infinitely possible SWCNT arrangements in LC. In this paper, we study solutions using synthetic data with a non-linear separating boundary. In addition, results for two real life datasets with partly merged classes are presented. The training process is based on a differential evolution (DE) algorithm, which subjects the SWCNT/LC material to repeated electrical charging, leading to progressive morphological and electric conductivity modifications. It is shown that the material configuration the DE algorithm converges to form a non-negligible part of the solution. Furthermore, the problem's complexity is relevant to the properties of the resulting "physical solver". The material structures created when training for a problem allow the retraining for a less complex one. The result is a doubly-trained material that keeps the memory of the original more complex problem. This is not the case for doubly-trained materials where initial training is for the less complex problem. The optimal electric field found by the DE algorithm is also a necessary solution component for the material's output to be interpreted as a computation.
AbstractList Evolution-in-materio is a form of unconventional computing combining materials' training and evolutionary search algorithms. In previous work, a mixture of single-walled-carbon-nanotubes (SWCNTs) dispersed in a liquid crystal (LC) was trained so that its morphology and electrical properties were gradually changed to perform a computational task. Material-based computation is treated as an optimisation problem with a hybrid search space consisting of the voltages used for creating the electrical field and the material's infinitely possible SWCNT arrangements in LC. In this paper, we study solutions using synthetic data with a non-linear separating boundary. In addition, results for two real life datasets with partly merged classes are presented. The training process is based on a differential evolution (DE) algorithm, which subjects the SWCNT/LC material to repeated electrical charging, leading to progressive morphological and electric conductivity modifications. It is shown that the material configuration the DE algorithm converges to form a non-negligible part of the solution. Furthermore, the problem's complexity is relevant to the properties of the resulting "physical solver". The material structures created when training for a problem allow the retraining for a less complex one. The result is a doubly-trained material that keeps the memory of the original more complex problem. This is not the case for doubly-trained materials where initial training is for the less complex problem. The optimal electric field found by the DE algorithm is also a necessary solution component for the material's output to be interpreted as a computation.
Author Vissol-Gaudin, E.
Kotsialos, A.
Groves, C.
Pearson, C.
Zeze, D. A.
Petty, M. C.
Author_xml – sequence: 1
  givenname: E.
  surname: Vissol-Gaudin
  fullname: Vissol-Gaudin, E.
  email: eleonore.vissol-gaudin@durham.ac.uk
  organization: Sch. of Eng. & Comput. Sci., Durham Univ., Durham, UK
– sequence: 2
  givenname: A.
  surname: Kotsialos
  fullname: Kotsialos, A.
  email: apostolos.kotsialos@durham.ac.uk
  organization: Sch. of Eng. & Comput. Sci., Durham Univ., Durham, UK
– sequence: 3
  givenname: C.
  surname: Groves
  fullname: Groves, C.
  email: chris.groves@durham.ac.uk
  organization: Sch. of Eng. & Comput. Sci., Durham Univ., Durham, UK
– sequence: 4
  givenname: C.
  surname: Pearson
  fullname: Pearson, C.
  email: christopher.pearson@durham.ac.uk
  organization: Sch. of Eng. & Comput. Sci., Durham Univ., Durham, UK
– sequence: 5
  givenname: D. A.
  surname: Zeze
  fullname: Zeze, D. A.
  email: d.a.zeze@durham.ac.uk
  organization: Sch. of Eng. & Comput. Sci., Durham Univ., Durham, UK
– sequence: 6
  givenname: M. C.
  surname: Petty
  fullname: Petty, M. C.
  email: m.c.petty@durham.ac.uk
  organization: Sch. of Eng. & Comput. Sci., Durham Univ., Durham, UK
BookMark eNo1z81KxDAUBeAIutBxHkDc5AVac3PbJHU3E_wZGFF0XA9pk0igTUtSF769BcfVWXxwOOeKnMcxOkJugJUArLnb6XddcgayVMBRSHlG1o1UUKMSUNfYXJIPPQ7T9xziF92a7CwdI30xs0vB9PSQTIgL3dPNNPWhM3NYeB7pNkSTfqjuTc7B_8NbGtveDfmaXHjTZ7c-5Yp8Pj4c9HOxf33a6c2-CIAoCzC17KQH2zDFpGfcgqgE95a5VvKWMaY6tJ3nvPK8aQVWAr2o0XTWcnAKV-T2rzc4545TCsMy6ni6ir8e6k0K
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICRC.2017.8123677
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Xplore
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Explore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781538615539
1538615533
EndPage 8
ExternalDocumentID 8123677
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i1337-1a57c7f1d90807f02d16462fd0eb72b0008c3dcf224f29b63463f653acdd21e83
IEDL.DBID RIE
IngestDate Thu Jun 29 18:37:36 EDT 2023
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i1337-1a57c7f1d90807f02d16462fd0eb72b0008c3dcf224f29b63463f653acdd21e83
OpenAccessLink https://durham-repository.worktribe.com/output/1146200
PageCount 8
ParticipantIDs ieee_primary_8123677
PublicationCentury 2000
PublicationDate 2017-Nov.
PublicationDateYYYYMMDD 2017-11-01
PublicationDate_xml – month: 11
  year: 2017
  text: 2017-Nov.
PublicationDecade 2010
PublicationTitle 2017 IEEE International Conference on Rebooting Computing (ICRC)
PublicationTitleAbbrev ICRC
PublicationYear 2017
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.6830394
Snippet Evolution-in-materio is a form of unconventional computing combining materials' training and evolutionary search algorithms. In previous work, a mixture of...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Complexity theory
Current measurement
Hardware
Liquids
Nanotubes
Optimization
Training
Title Computing Based on Material Training: Application to Binary Classification Problems
URI https://ieeexplore.ieee.org/document/8123677
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NS8NAEB3a4sGTSit-swePbptsPibxZotFQUvQKr2VZGcXekmkTf397m5Ci-DFW9iEDcxseLuZee8B3FKuQpVQyONUJzyMMOeFROREaeBpEpF2OgWfLzibJYtFmnXgbseFUUq55jM1tJeulk-V3NpfZaPE6Y1hF7qIccPVaguVvpeOnidvE9urhcP2uV-GKQ4vpkf_e9MxDPbEO5btIOUEOqrsw3vjvGAG2NhgDrGqZK957ZYOm7cWD_fsYV-KZnXFxo5oy5zppW0Ham5kjX_MZgAf08f55Im3Xgh8ZU6RyP08Qonap9Rs8VB7gqwwmNDkqQKFg3IZkNQGkbVIizgI40DHUZBLIuGrJDiFXlmV6gyYleDT5qCE9os1iSmE9k3CCpMZ0mbOc-jbgCy_GrmLZRuLi7-HL-HQxryh511Br15v1TUcyO96tVnfuBz9ALyNlag
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFH5BNNGTGjDizx48Wti6H928CZFAHIQoGm5k62sTLpuB4d9v2y0QEy_elm7pkve6fO3e-74P4AFT6csIfRrGKqJ-wFOaCc4pYuw5ClmgrE7BZ8Kn02ixiGcNeNxxYaSUtvlMds2lreVjIbbmV1kvsnpj_AAOA99nTsXWqkuVrhP3xoO3genW4t36yV-WKRYxhqf_e9cZtPfUOzLbgco5NGTegvfKe0EPkL5GHSRFTiZpaRcPmdcmD0_keV-MJmVB-pZqS6ztpWkIqm7MKgeZTRs-hi_zwYjWbgh0pc-RnLppwAVXLsZ6k8eVw9BIgzGFjsw4s2AuPBRKY7JicRZ6fuipMPBSgchcGXkX0MyLXF4CMSJ8Sh-VuPlmdWoyplydskznBpWeswMtE5DlVyV4saxjcfX38D0cj-aTZJmMp6_XcGLiX5H1bqBZrrfyFo7Ed7narO9svn4AtLmY7w
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=2017+IEEE+International+Conference+on+Rebooting+Computing+%28ICRC%29&rft.atitle=Computing+Based+on+Material+Training%3A+Application+to+Binary+Classification+Problems&rft.au=Vissol-Gaudin%2C+E.&rft.au=Kotsialos%2C+A.&rft.au=Groves%2C+C.&rft.au=Pearson%2C+C.&rft.date=2017-11-01&rft.pub=IEEE&rft.spage=1&rft.epage=8&rft_id=info:doi/10.1109%2FICRC.2017.8123677&rft.externalDocID=8123677