id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_wkagp4tokffrvohruolrcry5kq	Stephen J. Gotts	Neural network-expert system models of relative-depth perception	1995	5	.pdf	application/pdf	3214	321	61	Neural network-expert system models of relative-depth perception Degree of binocular, horizontal disparity was used by two hybrid neural network/expert system computer models to make relative-depth judgments for pairs of stimulus points. showed that horizontal disparity could be computed by the shift in activated cortical hypercolumns Simulation 2 corrected for this inaccuracy by appropriately weighting a stimulus point's disparity value as a function at some point in the visual field, forming a depth reference area known as the horopter (Ogle, 1964). The output layer of the neural network consisted ofa 2 X 20 matrix representing hypercolumns found in Area V 1 of the visual The small inaccuracy ofthe model was due to a slight shift of the stimulus points for a given hypercolumn disparity toward the first simulation with a function that corrects each stimulus point's disparity value on the basis of its horizontal made by the model in Simulation 2, allowsfor more accurate relative-depth judgments.	./cache/work_wkagp4tokffrvohruolrcry5kq.pdf	./txt/work_wkagp4tokffrvohruolrcry5kq.txt