id:"swepub:oai:DiVA.org:kth-329366"
Search: id:"swepub:oai:DiVA.org:kth-329366" > Brain-like Combinat...
- 1 of 1
- Previous record
- Next record
- To hitlist
- Ravichandran, Naresh BalajiKTH,Beräkningsvetenskap och beräkningsteknik (CST),Computational Cognitive Brain Science Group (author)
Brain-like Combination of Feedforward and Recurrent Network Components Achieves Prototype Extraction and Robust Pattern Recognition
- Article/chapterEnglish2023
Publisher, publication year, extent ...
- 2023-03-10
- Cham :Springer Nature,2023
- printrdacarrier
Numbers
- LIBRIS-ID:oai:DiVA.org:kth-329366
- https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-329366URI
- https://doi.org/10.1007/978-3-031-25891-6_37DOI
- https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-326225URI
Supplementary language notes
- Language:English
- Summary in:English
Part of subdatabase
- SwePubSwePub
Classification
Notes
- QC 20230621
- QC 20230503
- Associative memory has been a prominent candidate for the computation performed by the massively recurrent neocortical networks. Attractor networks implementing associative memory have offered mechanistic explanation for many cognitive phenomena. However, attractor memory models are typically trained using orthogonal or random patterns to avoid interference between memories, which makes them unfeasible for naturally occurring complex correlated stimuli like images. We approach this problem by combining a recurrent attractor network with a feedforward network that learns distributed representations using an unsupervised Hebbian-Bayesian learning rule. The resulting network model incorporates many known biological properties: unsupervised learning, Hebbian plasticity, sparse distributed activations, sparse connectivity, columnar and laminar cortical architecture, etc. We evaluate the synergistic effects of the feedforward and recurrent network components in complex pattern recognition tasks on the MNIST handwritten digits dataset. We demonstrate that the recurrent attractor component implements associative memory when trained on the feedforward-driven internal (hidden) representations. The associative memory is also shown to perform prototype extraction from the training data and make the representations robust to severely distorted input. We argue that several aspects of the proposed integration of feedforward and recurrent computations are particularly attractive from a machine learning perspective.
Subject headings and genre
- NATURVETENSKAP Matematik Beräkningsmatematik hsv//swe
- NATURAL SCIENCES Mathematics Computational Mathematics hsv//eng
- TEKNIK OCH TEKNOLOGIER Elektroteknik och elektronik Datorsystem hsv//swe
- ENGINEERING AND TECHNOLOGY Electrical Engineering, Electronic Engineering, Information Engineering Computer Systems hsv//eng
- Attractor
- Associative memory
- Unsupervised learning
- Hebbian learning
- Recurrent networks
- Feedforward networks
- Brain-like computing
- Datalogi
Added entries (persons, corporate bodies, meetings, titles ...)
- Lansner, Anders,Professor,1949-KTH,Beräkningsvetenskap och beräkningsteknik (CST),Stockholm Univ, Dept Math, Stockholm, Sweden.,Computational Cognitive Brain Science Group(Swepub:kth)u12s8cr8 (author)
- Herman, Pawel,1979-KTH,Beräkningsvetenskap och beräkningsteknik (CST),Computational Cognitive Brain Science Group(Swepub:kth)u19pqm1e (author)
- KTHBeräkningsvetenskap och beräkningsteknik (CST) (creator_code:org_t)
Related titles
- In:Lecture Notes in Computer ScienceCham : Springer Nature, s. 488-501
Internet link
- https://link.springer.com/chapter/10.1007/978-3-031-25891-6_37Publisher
- https://kth.diva-portal.org/smash/get/diva2:1753549/FULLTEXT01.pdffulltext:print
- https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-329366
- https://doi.org/10.1007/978-3-031-25891-6_37
- https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-326225
To the university's database
- 1 of 1
- Previous record
- Next record
- To hitlist
Find more in SwePub
- By the author/editor
- Ravichandran, Na ...
- Lansner, Anders, ...
- Herman, Pawel, 1 ...
- About the subject
-
- NATURAL SCIENCES
- NATURAL SCIENCES
- and Mathematics
- and Computational Ma ...
-
- ENGINEERING AND TECHNOLOGY
- ENGINEERING AND ...
- and Electrical Engin ...
- and Computer Systems
- Articles in the publication
- Lecture Notes in ...
- By the university
- Royal Institute of Technology
Search outside SwePub
- Extend your search to:
- Google Book Search
- Google Scholar
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
- Copyright © LIBRIS - National Library Systems
- LIBRIS.kb.se
