Show Reference: "A neurodynamical cortical model of visual attention and invariant object recognition."

A neurodynamical cortical model of visual attention and invariant object recognition. Vision Research, Vol. 44, No. 6. (March 2004), pp. 621-642 by Gustavo Deco, Edmund T. Rolls
@article{deco-and-rolls-2004,
    abstract = {We describe a model of invariant visual object recognition in the brain that incorporates feedback biasing effects of top-down attentional mechanisms on a hierarchically organized set of visual cortical areas with convergent forward connectivity, reciprocal feedback connections, and local intra-area competition. The model displays space-based and object-based covert visual search by using attentional top-down feedback from either the posterior parietal or the inferior temporal cortex ({IT}) modules, and interactions between the two processing streams occurring in V1 and V2. The model explains the gradually increasing magnitude of the attentional modulation that is found in {fMRI} experiments from earlier visual areas (V1, V2) to higher ventral stream visual areas (V4, {IT}); how the effective size of the receptive fields of {IT} neurons becomes smaller in natural cluttered scenes; and makes predictions about interactions between stimuli in their receptive fields.},
    address = {Department of Technology, Computational Neuroscience, Instituci\~{o} Catalana de Recerca i Estudis Avan\c{c}ats, Universitat Pompeu Fabra, Passeig de Circumval.laci\'{o}, 08003 Barcelona, Spain.},
    author = {Deco, Gustavo and Rolls, Edmund T.},
    issn = {0042-6989},
    journal = {Vision Research},
    keywords = {ann, architecture, attention, biology, bottom-up, computational, inhibition, model, perception, spiking, suppression, top-down, visual, visual-processing},
    month = mar,
    number = {6},
    pages = {621--642},
    pmid = {14693189},
    posted-at = {2012-08-09 10:59:18},
    priority = {0},
    title = {A neurodynamical cortical model of visual attention and invariant object recognition.},
    url = {http://view.ncbi.nlm.nih.gov/pubmed/14693189},
    volume = {44},
    year = {2004}
}

See the CiteULike entry for more info, PDF links, BibTex etc.

Deco and Rolls introduce a system that uses a trace learning rule to learn recognition of more and more complex visual features in successive layers of a neural architecture. In each layer, the specificity of the features increases together with the receptive fields of neurons until the receptive fields span most of the visual range and the features actually code for objects. This model thus is a model of the development of object-based attention.