by C.J. Rozell, I.N. Goodman and D.H. Johnson
Abstract:
We present a simple but general model for feature-based information processing with selective attention. We model feature extraction as projections onto frames of subspaces, which accounts for redundancies in the representations of individual features as well as between features. To manage limited resources, we use feedback attentional signals to dynamically allocate system resources according to the observed events. In our model, attention maximizes the average information retained about all events weighted by their relative priorities. We illustrate the model with a simple system under a total bit constraint and discuss how the organization of the feature extraction affects the optimal bit allocation.
Reference:
Feature-based information processing with selective attentionC.J. Rozell, I.N. Goodman and D.H. Johnson. May 2006.
Bibtex Entry:
@CONFERENCE{rozell.05b,
author = {Rozell, C.J. and Goodman, I.N. and Johnson, D.H.},
title = {Feature-based information processing with selective attention},
booktitle = {{Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP)}},
year = {2006},
address = {Toulouse, France},
month = {May},
abstract = {We present a simple but general model for feature-based
information processing with selective attention. We model
feature extraction as projections onto frames of subspaces,
which accounts for redundancies in the representations of
individual features as well as between features. To manage
limited resources, we use feedback attentional signals to
dynamically allocate system resources according to the
observed events. In our model, attention maximizes the
average information retained about all events weighted by
their relative priorities. We illustrate the model with a
simple system under a total bit constraint and discuss how
the organization of the feature extraction affects the
optimal bit allocation.},
url = {http://siplab.gatech.edu/pubs/rozellICASSP2006.pdf}
}