From ANN to Biomimetic Information Processing
2009 (English)In: BIOLOGICALLY INSPIRED SIGNAL PROCESSING FOR CHEMICAL SENSING / [ed] Gutierrez A, Marco S, 2009, Vol. 188, 33-43 p.Conference paper (Refereed)
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.
Place, publisher, year, edition, pages
2009. Vol. 188, 33-43 p.
, Studies in Computational Intelligence, ISSN 1860-949X
IdentifiersURN: urn:nbn:se:kth:diva-30835DOI: 10.1007/978-3-642-00176-5_2ISI: 000266719500002ScopusID: 2-s2.0-62549146707ISBN: 978-3-642-00175-8OAI: oai:DiVA.org:kth-30835DiVA: diva2:403007
OSPEL Workshop on Bio-inspired Signal Processing Barcelona, SPAIN, 2007
QC 201103102011-03-102011-03-042013-05-15Bibliographically approved