LAUSR

The polarity conversion sequence directly determines polarity conversion efficiency and then affects polarity optimization efficiency. However, few studies have focused on the polarity conversion sequence problem of Reed-Muller (RM) circuits. In this paper, we propose a continuous Hopfield neural network (CHNN)-based polarity conversion algorithm (CHNNPCA) for Mixed Polarity RM (MPRM) circuits, which uses the CHNN to solve the best polarity conversion sequence of polarity set waiting for evaluation before converting the polarity set. Moreover, based on the CHNNPCA, a polarity optimization algorithm (POA) is proposed to improve the polarity optimization efficiency of MPRM circuits. The experimental results on MCNC benchmark circuits show that for the large-scale polarity set, the CHNNPCA is superior to the mixed polarity conversion algorithm based on the tabular technique in terms of polarity conversion efficiency. Furthermore, compared to the traditional polarity optimization algorithm neglecting polarity conversion sequence, the POA has a considerable advantage in improving polarity optimization efficiency, especially for large-scale circuits. The POA can be extended to improve the polarity optimization efficiency of fixed polarity RM circuits.