Abstract
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.
Highlights
The computational skills of the human brain are a wonder, so it is easy to understand why many research engineers are interested in developing neuromorphic circuits, i.e., electronic implementation of neuron mechanisms
We are all impressed by the ability of the human brain to register and store vast quantities of visual information
It is understood that the retina has anatomical and physiological filters that can effectively encode image information, but often the functioning of visual cortex is seen as a tabula rasa
Summary
The computational skills of the human brain are a wonder, so it is easy to understand why many research engineers are interested in developing neuromorphic circuits, i.e., electronic implementation of neuron mechanisms. The anatomy and physiology of its visual cortex are already sufficient to mediate perception of objects, depth, and motion, as evidenced by the effectiveness of its behavior. Experimental study of the anatomy and physiology of cortical systems affirms the pre-programmed complexity, some of which will be discussed subsequently. The relevance, at this point, is to convey my belief that the most common approach to neural network design has been a mistake. I will make the case that none of these visual skills are unique to the human brain, or even the brains of mammals.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
