Peer-Reviewed Journal Details
Mandatory Fields
Jaramillo S.;Pearlmutter B.
2004
June
Neurocomputing
A normative model of attention: Receptive field modulation
Published
()
Optional Fields
Attention Learning Neural coding Receptive field
58-60
613
618
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. © 2003 Published by Elsevier B.V.
0925-2312
10.1016/j.neucom.2004.01.103
Grant Details