Bio-Inspired Imprecise Computational Blocks for Efficient VLSI Implementation of Soft-Computing Applications

TLDR

Conventional digital hardware blocks compute precise results for assigned calculations. The paper proposes Bio‑Inspired Imprecise Computational blocks that estimate results instead of computing precise values, aiming to reduce cost. The authors design BIC adders and multipliers, detailing their error behaviors and synthesis results. The BICs achieve greater area, speed, and power efficiency than precise counterparts and enable efficient implementation of a three‑layer face‑recognition neural network and a fuzzy processor’s defuzzification block.

Abstract

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