HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Roelfsema, P. R. Articles by van Ooyen, A. Search for Related Content PubMed PubMed Citation Articles by Roelfsema, P. R. Articles by van Ooyen, A.

Attention-Gated Reinforcement Learning of Internal Representations for Classification

p.roelfsema{at}ioi.knaw.nl, Netherlands Ophthalmic Research Institute, 1105 BA Amsterdam, Netherlands, and Center for Neurogenomics and Cognitive Research, Department of Experimental Neurophysiology, Vrije Universiteit, 1081 HV Amsterdam, Netherlands

Arjen van Ooyen

Arjen.van.ooyen{at}falw.vu.nl, Netherlands Institute for Brain Research, 1105 AZ Amsterdam, Netherlands, and Center for Neurogenomics and Cognitive Research, Department of Experimental Neurophysiology, Vrije Universiteit, 1081 HV Amsterdam, Netherlands

Animal learning is associated with changes in the efficacy of connections between neurons. The rules that govern this plasticity can be tested in neural networks. Rules that train neural networks to map stimuli onto outputs are given by supervised learning and reinforcement learning theories. Supervised learning is efficient but biologically implausible. In contrast, reinforcement learning is biologically plausible but comparatively inefficient. It lacks a mechanism that can identify units at early processing levels that play a decisive role in the stimulus-response mapping. Here we show that this so-called credit assignment problem can be solved by a new role for attention in learning. There are two factors in our new learning scheme that determine synaptic plasticity: (1) a reinforcement signal that is homogeneous across the network and depends on the amount of reward obtained after a trial, and (2) an attentional feedback signal from the output layer that limits plasticity to those units at earlier processing levels that are crucial for the stimulus-response mapping. The new scheme is called attention-gated reinforcement learning (AGREL). We show that it is as efficient as supervised learning in classification tasks. AGREL is biologically realistic and integrates the role of feedback connections, attention effects, synaptic plasticity, and reinforcement learning signals into a coherent framework.

This article has been cited by other articles:

				J. Triesch Synergies between intrinsic and synaptic plasticity mechanisms. Neural Comput., April 1, 2007; 19(4): 885 - 909. [Abstract] [Full Text] [PDF]

				S. Raiguel, R. Vogels, S. G. Mysore, and G. A. Orban Learning to see the difference specifically alters the most informative V4 neurons. J. Neurosci., June 14, 2006; 26(24): 6589 - 6602. [Abstract] [Full Text] [PDF]