SynergicLearning: Neural Network-Based Feature Extraction for Highly-Accurate Hyperdimensional Learning

Machine learning models differ in terms of accuracy, computational/memory complexity, training time, and adaptability among other characteristics. For example, neural networks (NNs) are well-known for their high accuracy due to the quality of their automatic feature extraction while brain-inspired h...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Digest of technical papers - IEEE/ACM International Conference on Computer-Aided Design s. 1 - 9
Hlavní autoři: Nazemi, Mahdi, Esmaili, Amirhossein, Fayyazi, Arash, Pedram, Massoud
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: Association on Computer Machinery 02.11.2020
Témata:
ISSN:1558-2434
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Machine learning models differ in terms of accuracy, computational/memory complexity, training time, and adaptability among other characteristics. For example, neural networks (NNs) are well-known for their high accuracy due to the quality of their automatic feature extraction while brain-inspired hyperdimensional (HD) learning models are famous for their quick training, computational efficiency, and adaptability. This work presents a hybrid, synergic machine learning model that excels at all the said characteristics and is suitable for incremental, on-line learning on a chip. The proposed model comprises an NN and a classifier. The NN acts as a feature extractor and is specifically trained to work well with the classifier that employs the HD computing framework. This work also presents a parameterized hardware implementation of the said feature extraction and classification components while introducing a compiler that maps any arbitrary NN and/or classifier to the aforementioned hardware. The proposed hybrid machine learning model has the same level of accuracy (i.e. ±1%) as NNs while achieving at least 10% improvement in accuracy compared to HD learning models. Additionally, the end-to-end hardware realization of the hybrid model improves power efficiency by 1.60x compared to state-of-the-art, high-performance HD learning implementations while improving latency by 2.13x. These results have profound implications for the application of such synergic models in challenging cognitive tasks.
AbstractList Machine learning models differ in terms of accuracy, computational/memory complexity, training time, and adaptability among other characteristics. For example, neural networks (NNs) are well-known for their high accuracy due to the quality of their automatic feature extraction while brain-inspired hyperdimensional (HD) learning models are famous for their quick training, computational efficiency, and adaptability. This work presents a hybrid, synergic machine learning model that excels at all the said characteristics and is suitable for incremental, on-line learning on a chip. The proposed model comprises an NN and a classifier. The NN acts as a feature extractor and is specifically trained to work well with the classifier that employs the HD computing framework. This work also presents a parameterized hardware implementation of the said feature extraction and classification components while introducing a compiler that maps any arbitrary NN and/or classifier to the aforementioned hardware. The proposed hybrid machine learning model has the same level of accuracy (i.e. ±1%) as NNs while achieving at least 10% improvement in accuracy compared to HD learning models. Additionally, the end-to-end hardware realization of the hybrid model improves power efficiency by 1.60x compared to state-of-the-art, high-performance HD learning implementations while improving latency by 2.13x. These results have profound implications for the application of such synergic models in challenging cognitive tasks.
Author Fayyazi, Arash
Nazemi, Mahdi
Esmaili, Amirhossein
Pedram, Massoud
Author_xml – sequence: 1
  givenname: Mahdi
  surname: Nazemi
  fullname: Nazemi, Mahdi
  email: mnazemi@usc.edu
  organization: University of Southern California
– sequence: 2
  givenname: Amirhossein
  surname: Esmaili
  fullname: Esmaili, Amirhossein
  email: esmailid@usc.edu
  organization: University of Southern California
– sequence: 3
  givenname: Arash
  surname: Fayyazi
  fullname: Fayyazi, Arash
  email: fayyazi@usc.edu
  organization: University of Southern California
– sequence: 4
  givenname: Massoud
  surname: Pedram
  fullname: Pedram, Massoud
  email: pedram@usc.edu
  organization: University of Southern California
BookMark eNo1jj1PwzAURQ0CiVI6M7DkD6T449mx2UrVUqQIBmCu7PglWLRO5aSC_HuCgOne4dyje0nOYhuRkGtG54yBvBVAqaB8LoBJZdQJmZlCM6UkcMFBnJIJk1LnY4ULMuu64CgABWm0npDmZYiYmlCVaFMMsbnLnvCY7G6M_rNNH_m97dBna7T9MWG2-uqTrfrQxqxuU7YJzftuyBdVNW56zDbDAZMPe4zdiIyWf-0VOa_trsPZX07J23r1utzk5fPD43JR5pZD0eeyNtpwA368WBkvpK6doUoaAOOUFg69ZKrwDrkrfkAuqTMMqFdFUXsUU3Lz6w2IuD2ksLdp2BoulWIgvgFuVFlp
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1145/3400302.3415696
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9781665423243
1665423242
EISSN 1558-2434
EndPage 9
ExternalDocumentID 9256614
Genre orig-research
GrantInformation_xml – fundername: National Science Foundation
  funderid: 10.13039/501100001809
GroupedDBID 6IE
6IF
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
FEDTE
IEGSK
IJVOP
M43
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-a247t-5f989294d044c9d358fb90659449b683bed5167dbe2b79294250b9140d677fde3
IEDL.DBID RIE
ISICitedReferencesCount 13
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000671087100089&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:28:38 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a247t-5f989294d044c9d358fb90659449b683bed5167dbe2b79294250b9140d677fde3
PageCount 9
ParticipantIDs ieee_primary_9256614
PublicationCentury 2000
PublicationDate 2020-Nov.-2
PublicationDateYYYYMMDD 2020-11-02
PublicationDate_xml – month: 11
  year: 2020
  text: 2020-Nov.-2
  day: 02
PublicationDecade 2020
PublicationTitle Digest of technical papers - IEEE/ACM International Conference on Computer-Aided Design
PublicationTitleAbbrev ICCAD
PublicationYear 2020
Publisher Association on Computer Machinery
Publisher_xml – name: Association on Computer Machinery
SSID ssib044045988
ssj0020286
Score 2.2332265
Snippet Machine learning models differ in terms of accuracy, computational/memory complexity, training time, and adaptability among other characteristics. For example,...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms adaptability
Adaptation models
arbitrary NN
Artificial neural networks
automatic feature extraction
brain-inspired hyperdimensional learning models
classification components
computational efficiency
Computational modeling
Data models
end-to-end hardware realization
feature extraction
feature extractor
HD computing framework
HD learning models
high-performance HD
highly-accurate hyperdimensional learning
hybrid machine learning model
hybrid model
Hyperdimensional Learning
learning (artificial intelligence)
machine learning models
neural nets
neural network-based feature extraction
neural networks
On-line Learning
online learning
Parallel Processing
parameterized hardware implementation
synergic machine learning model
synergic models
Training
Training data
training time
Title SynergicLearning: Neural Network-Based Feature Extraction for Highly-Accurate Hyperdimensional Learning
URI https://ieeexplore.ieee.org/document/9256614
WOSCitedRecordID wos000671087100089&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/eLvHCXMwlV07T8MwELZKxQALjxbxlgdG0jaOY8dsgFp1QFUlQOpW1a-qUmlRSBD999y5oWVgYYoVRU50vujus-_7jpAbr5jJhMWCpziLuBYafinvI2MsS5T3ncwGdf0nORhko5Ea1sjthgvjnAvFZ66Fw3CWb5emxK2ytoL4LLBr9Y6UYs3V-vEdlLlLg_RWBbYgbopKyifmaTvh6M6slSBgCQr9214qIZT0Dv73EYekueXk0eEm2hyRmlsck_1fcoINMn1eIZNvZirR1OkdRe2NyRwuodg7eoCYZSmmfWXuaPeryNe8BgqpK8WSj_kqujemRP0I2geICu7zhiXumK_Tn2mb5LXXfXnsR1UjhWjCuCyi1KsM0iBuwUxG2STNvFZ4oMq50iJLtLNpLKTVjmmJD0JepBVALyuk9NYlJ6S-WC7cKVK8kctqJjHrWIBmYPGO9N7G8AruFE_PSANNNn5fa2WMK2ud_337guwxxK-4TcsuSb3IS3dFds1nMfvIr8MCfwPBt6aN
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8JAEN4QNFEvPsD4dg8eLdDt9rHe1EAwIiERE26EfRESBFNbI__emaWABy-eummabTM7zcy3O983hNxYwVQSaSx48hOPy0jCL2Wtp5RmgbC2kWinrt-Ju91kMBC9Erldc2GMMa74zNRw6M7y9VzluFVWFxCfI-xavRVyzhpLttbKe1DoLnTiWwXcgsgZFWI-Pg_rAUeHZrUAIYvT6N90U3HBpLX_v884INUNK4_21vHmkJTM7Ijs_RIUrJDx6wK5fBNVyKaO7yiqb4ymcHHl3t4DRC1NMfHLU0Ob31m6ZDZQSF4pFn1MF969UjkqSNA2gFRwoHcscseMna6mrZK3VrP_2PaKVgreiPE480IrEkiEuAYzKaGDMLFS4JEq50JGSSCNDv0o1tIwGeODkBlJAeBLR3FstQmOSXk2n5kTJHkjm1WNfNbQAM7A4o3YWu3DK7gRPDwlFTTZ8GOpljEsrHX29-1rstPuv3SGnafu8znZZYhmcdOWXZBylubmkmyrr2zymV65xf4Bmo2p1A
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=Digest+of+technical+papers+-+IEEE%2FACM+International+Conference+on+Computer-Aided+Design&rft.atitle=SynergicLearning%3A+Neural+Network-Based+Feature+Extraction+for+Highly-Accurate+Hyperdimensional+Learning&rft.au=Nazemi%2C+Mahdi&rft.au=Esmaili%2C+Amirhossein&rft.au=Fayyazi%2C+Arash&rft.au=Pedram%2C+Massoud&rft.date=2020-11-02&rft.pub=Association+on+Computer+Machinery&rft.eissn=1558-2434&rft.spage=1&rft.epage=9&rft_id=info:doi/10.1145%2F3400302.3415696&rft.externalDocID=9256614