作者: H R Mahdiani , A Ahmadi , S M Fakhraie , C Lucas
DOI: 10.1109/TCSI.2009.2027626
关键词:
摘要: The conventional digital hardware computational blocks with different structures are designed to compute the precise results of assigned calculations. main contribution our proposed Bio-inspired Imprecise Computational (BICs) is that they provide an applicable estimation result instead its value at a lower cost. These novel more efficient in terms area, speed, and power consumption respect their rivals. Complete descriptions sample BIC adder multiplier as well error behaviors synthesis introduced this paper. It then shown these can be exploited efficiently implement three-layer face recognition neural network defuzzification block fuzzy processor.