Sökning: onr:"swepub:oai:DiVA.org:kth-30835" >
From ANN to Biomime...
-
Lansner, AndersKTH,Beräkningsbiologi, CB
(författare)
From ANN to Biomimetic Information Processing
- Artikel/kapitelEngelska2009
Förlag, utgivningsår, omfång ...
-
Berlin, Heidelberg :Springer Berlin Heidelberg,2009
-
printrdacarrier
Nummerbeteckningar
-
LIBRIS-ID:oai:DiVA.org:kth-30835
-
https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-30835URI
-
https://doi.org/10.1007/978-3-642-00176-5_2DOI
Kompletterande språkuppgifter
-
Språk:engelska
-
Sammanfattning på:engelska
Ingår i deldatabas
Klassifikation
-
Ämneskategori:ref swepub-contenttype
-
Ämneskategori:kon swepub-publicationtype
Anmärkningar
-
QC 20110310
-
Artificial neural networks (ANN) are useful components in today's data analysis toolbox. They were initially inspired by the brain but are today accepted to be quite different from it. ANN typically lack scalability and mostly rely on supervised learning, both of which are biologically implausible features. Here we describe and evaluate a novel cortex-inspired hybrid algorithm. It is found to perform on par with a Support Vector Machine (SVM) in classification of activation patterns from the rat olfactory bulb. On-line unsupervised learning is shown to provide significant tolerance to sensor drift, an important property of algorithms used to analyze chemo-sensor data. Scalability of the approach is illustrated on the MNIST dataset of handwritten digits.
Ämnesord och genrebeteckningar
Biuppslag (personer, institutioner, konferenser, titlar ...)
-
Benjaminsson, SimonKTH,Beräkningsbiologi, CB(Swepub:kth)u1lqnxb3
(författare)
-
Johansson, ChristopherKTH,Beräkningsbiologi, CB(Swepub:kth)u1s42xk3
(författare)
-
KTHBeräkningsbiologi, CB
(creator_code:org_t)
Sammanhörande titlar
-
Ingår i:BIOLOGICALLY INSPIRED SIGNAL PROCESSING FOR CHEMICAL SENSINGBerlin, Heidelberg : Springer Berlin Heidelberg, s. 33-439783642001758
Internetlänk
Hitta via bibliotek
Till lärosätets databas