From ANN to Biomimetic Information Processing

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.

Benjaminsson, SimonKTH,Beräkningsbiologi, CB(Swepub:kth)u1lqnxb3 (författare)
Johansson, ChristopherKTH,Beräkningsbiologi, CB(Swepub:kth)u1s42xk3 (författare)
KTHBeräkningsbiologi, CB (creator_code:org_t)

Ingår i:BIOLOGICALLY INSPIRED SIGNAL PROCESSING FOR CHEMICAL SENSINGBerlin, Heidelberg : Springer Berlin Heidelberg, s. 33-439783642001758

Av författaren/redakt...: Lansner, Anders; Benjaminsson, Si ...; Johansson, Chris ...

Om ämnet

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.