Fast and robust learning by reinforcement signals: explorations in the insect brain.

Full Abstract

We propose a model for pattern recognition in the insect brain. Departing from a well-known body of knowledge about the insect brain, we investigate which of the potentially present features may be useful to learn input patterns rapidly and in a stable manner. The plasticity underlying pattern recognition is situated in the insect mushroom bodies and requires an error signal to associate the stimulus with a proper response. As a proof of concept, we used our model insect brain to classify the well-known MNIST database of handwritten digits, a popular benchmark for classifiers. We show that the structural organization of the insect brain appears to be suitable for both fast learning of new stimuli and reasonable performance in stationary conditions. Furthermore, it is extremely robust to damage to the brain structures involved in sensory processing. Finally, we suggest that spatiotemporal dynamics can improve the level of confidence in a classification decision. The proposed approach allows testing the effect of hypothesized mechanisms rather than speculating on their benefit for system performance or confidence in its responses.

Author information

Author/s: Huerta, Ramón (R); Nowotny, Thomas (T);

Affiliation: Institute for Nonlinear Science, University of California San Diego, La Jolla CA 92093-0402, USA. rhuerta(-atsign-)ucsd.edu

Grants: BB/F005113/1 (Agency:Biotechnology and Biological Sciences Research Council)

Journal and publication information

Publication Type: Journal Article; Research Support, Non-U.S. Gov't

Journal: Neural computation (Neural Comput), published in United States. (Language: eng)

Reference: 2009-Aug; vol 21 (issue 8) : pp 2123-51

Dates: Created 2009/06/22; Completed 2009/09/15; Revised 2009/09/29;

PMID: 19538091, status: MEDLINE (last retrieval date: 9/29/2009, IMS Date: )

Sourced from the National Library of Medicine. Abstract text and other information may be subject to copyright.

Comments and Corrections

ErratumIn: Neural Comput. 2009 Sep;21(9):2713.

External Links for this article
(including full text providers, if available):

Click Electronic Full-text Provider Links to see options for finding the electronic full text links to this article. Note there may be a subscription or fee required for access to the full text. See our FAQ for information on finding FREE full text articles.

This article may also be located in paper journal collections available in many libraries. Use the Journal and Publication Information above to find the full article.