PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A hierarchical generative model of recurrent object-based attention in the visual cortex.
David Reichert, Peggy Series and Amos Storkey
Proceedings of ICANN 2011 2011.

Abstract

In line with recent work exploring Deep Boltzmann Machines (DBMs) as models of cortical processing, we demonstrate the potential of DBMs as models of object-based attention, combining generative principles with attentional ones. We show: (1) How inference in DBMs can be related qualitatively to theories of attentional recurrent processing in the visual cortex; (2) that deepness and topographic receptive fields are important for realizing the attentional state; (3) how more explicit attentional suppressive mechanisms can be implemented, depending crucially on sparse representations being formed during learning.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Machine Vision
Learning/Statistics & Optimisation
ID Code:8885
Deposited By:Amos Storkey
Deposited On:21 February 2012