Search results for key=RaB1997 : 1 match found.

Technical Reports

1997

@techreport{RaB1997,
	vgclass =	{report},
	vgproject =	{nn,invariance},
	author =	{Rajesh P. N. Rao and Dana H. Ballard},
	title =	{Localized Receptive Fields May Mediate
	Transformation-Invariant Recognition in the Visual Cortex},
	number =	{97.2},
	institution =	{Department of Computer Science, University of
	Rochester},
	address =	{Rochester, NY 14627},
	month =	{May},
	year =	{1997},
	abstract =	{Neurons in the visual cortex are known to possess
	localized, oriented receptive fields. It has previously been suggested
	that these distinctive properties may reflect an efficient image
	encoding strategy based on maximizing the sparseness of the
	distribution of output neuronal activities or alternatively, extracting
	the independent components of natural image ensembles. Here, we show
	that a relatively simple neural solution to the problem of
	transformation-invariant visual recognition also causes localized,
	oriented receptive fields to be learned from natural images. These
	receptive fields, which code for various transformations in the image
	plane, allow a pair of cooperating neural networks, one estimating
	object identity (``what'') and the other estimating object
	transformations (``where'') to simultaneously recognize an object and
	estimate its pose by jointly maximizing the \emph{a posteriori}
	probability of generating the observed visual data. We provide
	experimental results demonstrating the ability of these networks to
	factor retinal stimuli into object-centred features and
	object-invariant transformations. The resulting neuronal architecture
	suggests concrete computational roles for the neuroanatomical
	connections known to exist between the dorsal and ventral visual
	pathways.},
}