PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A hierarchical generative model of recurrent object-based attention in the visual cortex
David Reichert, Peggy Seriès and Amos Storkey
In: International Conference on Artificial Neural Networks (ICANN-11), 14-17 June 2011, Espoo, Finland.

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:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Theory & Algorithms
ID Code:8753
Deposited By:David Reichert
Deposited On:21 February 2012