Semiconductor technology is advancing to the point where devices will have the comlexity that is required to solve lower level perception tasks. The level of complexity required for higher cortical processing is still years away.
This technology has made possible a new discipline--synthetic neurobiology. The thesis of this discipline is that it is not possible, even in principle, to claim a full understanding of a system unless one is able to build one that functions properly. This principle is already well accepted in molecular biology and more recently in genetics.
Because biological systems generate on very different principles than do conventional systems, the ability to synthesize models of biological function results in a new engineering discipline. Systems using this new discipline have demonstrated real-time operation requiring far less power consumption than digital systems performing the same function. An example of this work can be seen in the labs of Carver Mead and Cristof Koch at Caltech.