I've been skeptical for a long time about the role of "learning" in the acquisition of the ability to see. Finally, one too many people gave a talk about how infants are "learning to see" during their first (years, months, whatever) of life. I took a seminar in Psychology on Cognitive Development and this technical report is the result. Vision, Learning, and Development
It seems to be a common feeling that animals learn to see, and this feeling, together with the re-emergence of computer learning paradigms that mimic many forms of human learning, has raised hopes that learning is the key to the computer vision problem. Indeed, it seems clear that Nature does not ``program'' all our visual capabilities into the genome, and we certainly know that programming a computer with a closed-form solution to the vision problem is a daunting task.
This aim of this informal and elementary report (basically a term paper) is to cast doubt on the idea that biological systems learn to see. The complex process of development, beginning at fertilization and ending with a mature individual, could be considered to have genetic and learning processes as endpoints. This report mostly considers what goes on between those endpoints, and is meant to raise the possibility that some of the least understood processes in biology are responsible for visual capabilities.
Back to Brown's Home Page
Back to URCS Faculty directory
Back to URCS Home Page