超分布超并行智能处理的竞争行波异步叠加方法

ASYNCHRONOUS SUPERIMPOSITION APPROACH OF COMPETITIVE WAVES FOR HYPER-DISTRIBUTED HYPER-PARALLEL INTELLIGENT PROCESSING

基于全局同步均质竞争行波的超分布超并行智能处理方法，虽能有效地解决传统的串行符号逻辑方法和通常的神经网络方法所存在的许多问题．但"全局性的同步和均质"这种限制在很多情况下难以满足．本文提出同步均质竞争行波的异步叠加方法，用于超分市超并行智能处理，比单一的全局同步均质竞争行波方法有更好的灵活性和实时处理性，能用于范围更广的问题求解，尤其适合于隐含与或图搜索．

It has been shown that the hyper-distributed hyper-parallel intelligentprocessing approach based on the global synchronous homogeneous competitivewaves can effectively overcorne many formidable obstacles, which present in the ap-proach based on the classical sequential symbolic logic or the ordinary neural net-works for the artificial intelligent problem solving. However, the constrain of theglobal synchronous and homogeneous propagation can not be always met in somepractical cases. This paper presents a new approach to hyper-distributed hyper-par-allel AI problem solving. which is based on the asynchronous superirnposition ofsgnchronous homogeneous concurrent competitive waves. The asynchronous super-imposition propagation can be regarded as a general case of the global synchronoushornogeneous ones, and as a special case of the general asynchronous heterogeneousones. In comparison with the global synchronous homogeneous mechanism in priorShuai's papers, the proposed approach has many significant advantages: the lesscomplexities in time and space, requirement of only small-degree synchronizationand homogeneity for wave media, much more suitability and feasibility for real-timeAI processing, especially for searching an implicit AND/OR graph, concurrent useof different heuristic functions for distinct local synchronous homogeneous waves,hierarchic architecture of concurrent AI problem solving, and the more feasible ap-plications.