Perspectives on computational perception and cognition under uncertainty

Abstract

This paper describes perspectives on computational perception and cognition under uncertainty. Humans often mimic nature in the development of machines. The human brain, particularly its faculty for perception and cognition, is the most intriguing models for developing intelligent systems. Human cognitive processes have a grant tolerance for imprecision or uncertainty. This is of great value in solving many engineering problems, as there are innumerable uncertainties in real-world phenomena. These uncertainties can be broadly classified under two categories: information arising from the random behavior of physical systems; and information arising from human perception and cognition processes, or from cognitive information in general. Statistical theory can be used to model the former, but lacks the sophistication two process the latter. The theory of fuzzy logic, initially met with much skepticism, has proven to be very effective in processing the latter. New computing methods based on fuzzy logic can lead to greater adaptability, tractability, robustness, as well as a lower cost solution in the development of intelligent systems.