A Stochastic Dynamic Local Search Method for Learning Multiple-Valued Logic Networks

Abstract

SUMMARY In this paper, we propose a stochastic dynamic local search(SDLS) method for Multiple-Valued Logic (MVL)learning by introducing stochastic dynamics into the traditional local search method. The proposed learning network maintains some trends of quick descent to either global minimum or a local minimum, and at the same time has some chance of escaping from local minima by permitting temporary error increases during learning. Thus the network may eventually reach the global minimum state or its best approximation with very high probability. Simulation results show that the proposed algorithm has the superior abilities to find the global minimum for the MVL network learning within reasonable number of iterations.

A Chaotic Clonal Selection Algorithm and its Application to Synthesize Multiple‐Valued Logic Functions

“…Especially, the two length strategies of antibody were compared. Then, compared with the error function utilized in the BP [10] and LS methods [11,12], the proposed affinity function that enabled the search to find minimized MVL functions with less product terms was verified. Moreover, the effect of the chaotic system taking on the CSA was also demonstrated.…”

“…Finally, we compared the experimental results of the four algorithms involving LS [11], SDLS [12], GA [15] and CCSA. In order to reduce the stochastic effect of the algorithms and make statistic comparisons, all the results were averaged over 20 randomly generated MVL functions and each function was run ten replications.…”

“…Several methodologies have been proposed in the literature for synthesis of MVL functions, such as deterministic algorithms [4], direct cover-based approaches [5][6][7], back-propagation methods (BP) [8][9][10], local search methods (LS) [11,12], genetic algorithms (GA) [13][14][15], and so on. These methodologies can be divided into two categories: the deterministic algorithms and direct cover-based approaches belong to technology-dependent approaches, whereas BP methods, LS methods and GA belong to technology-independent approaches.…”

“…However, during learning, many nodes and parameters such as weights and thresholds were usually necessary to approximate an MVL function and any knowledge which was available prior to training was unable to be used. Compared with the BP algorithms, the LS methods have easy hardware implementation and can widely make use of the prior knowledge we have on MVL while constructing an MVL network [11,17]. Recently, GA [18] were also proposed to constitute an important avenue for solving such a problem.…”

MVL-MIN: A New Heuristic Minimization Tool for Multiple-Valued Logic Functions

“…Therefore, most of the tools rely on heuristic minimization methods such as MVSIS [26]. In the literature, there are several methodologies reported for the synthesis of MVL functions, such as directcover-based approaches [27,28], network learning via local search methods [29,30], genetic algorithms [31,32,33], and artificial intelligence methods [34].…”