Jaramillo, Santiago and Pearlmutter, Barak A. (2004) A normative model of attention: receptive field modulation. Neurocomputing, 58-60. pp. 613-618. ISSN 0925-2312

Preview

Download (249kB) | Preview

Abstract

When sensory stimuli are encoded in a lossy fashion for efficient transmission, there are necessarily tradeoffs between the represented fidelity of various aspects of the stimuli. In the model of attention presented here, a top-down signal informs the encoder of these tradeoffs. Given the stimulus ensemble and tradeoff requirements, our system learns an optimal encoder. This general model is instantiated in a simple network: an autoencoder with a bottleneck, innervated by a top-down attentional signal, and trained using backpropagation. The modulation of neural activity learned by this model qualitatively matches that measured in animals during visual attention tasks.

Item Type:	Article
Keywords:	Attention; Neural coding; Learning; Receptive field;
Academic Unit:	Faculty of Science and Engineering > Computer Science
Item ID:	8120
Identification Number:	https://doi.org/10.1016/j.neucom.2004.01.103
Depositing User:	Barak Pearlmutter
Date Deposited:	05 Apr 2017 15:37
Journal or Publication Title:	Neurocomputing
Publisher:	Elsevier
Refereed:	Yes
URI:	http://www.sciencedirect.com

Repository Staff Only(login required)

Item control page

Downloads