id:"swepub:oai:DiVA.org:kth-19860"
Search: id:"swepub:oai:DiVA.org:kth-19860" > A palimpsest memory...
- 1 of 1
- Previous record
- Next record
- To hitlist
A palimpsest memory based on an incremental Bayesian learning rule
-
- Sandberg, Anders (author)
- KTH,Numerisk analys och datalogi, NADA
-
- Lansner, Anders (author)
- KTH,Numerisk analys och datalogi, NADA
-
- Petersson, K. M. (author)
- Karolinska Institutet
- show more...
- show less...
- (creator_code:org_t)
- 2000
- 2000
- English.
- In: Neurocomputing. - 0925-2312 .- 1872-8286. ; 32, s. 987-994
- Journal article (peer-reviewed)
Abstract
Subject headings
Close
- Capacity limited memory systems need to gradually forget old information in order to avoid catastrophic forgetting where all stored information is lost. This can be achieved by allowing new information to overwrite old, as in the so-called palimpsest memory. This paper describes a new such learning rule employed in an attractor neural network. The network does not exhibit catastrophic forgetting, has a capacity dependent on the learning time constant and exhibits recency effects in retrieval.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Bioinformatik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Bioinformatics (hsv//eng)
Keyword
- Bayesian Confidence Propagation
- palimpsest memory
- associative memory
- networks
- model
Publication and Content Type
- ref (subject category)
- art (subject category)
Find in a library
- Neurocomputing (Search for host publication in LIBRIS)
To the university's database
- 1 of 1
- Previous record
- Next record
- To hitlist
Find more in SwePub
- By the author/editor
- Sandberg, Anders
- Lansner, Anders
- Petersson, K. M.
- Ekeberg, Örjan
- About the subject
-
- NATURAL SCIENCES
- NATURAL SCIENCES
- and Computer and Inf ...
- and Bioinformatics
- Articles in the publication
- Neurocomputing
- By the university
- Royal Institute of Technology
- Karolinska Institutet
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
