学术文献库

A substantial amount of time and energy has been invested to develop machine vision using connectionist (neural network) principles. Most of that work has been inspired by theories advanced by neuroscientists and behaviorists for how cortical systems store stimulus information. Those theories call for information flow through connections among several neuron populations, with the initial connections being random (or at least non-functional). Then the strength or location of connections are modified through training trials to achieve an effective output, such as the ability to identify an object. Those theories ignored the fact that animals that have no cortex, e.g., fish, can demonstrate visual skills that outpace the best neural network models. Neural circuits that allow for immediate effective vision and quick learning have been preprogrammed by hundreds of millions of years of evolution and the visual skills are available shortly after hatching. Cortical systems may be providing advanced image processing, but most likely are using design principles that had been proven effective in simpler systems. The present article provides a brief overview of retinal and cortical mechanisms for registering shape information, with the hope that it might contribute to the design of shape-encoding circuits that more closely match the mechanisms of biological vision.