arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1105.1651cond-mat.dis-nncond-mat.stat-mechcs.ITmath.IT
收藏

二元突触网络学习的组合局部搜索策略

Combined local search strategy for learning in networks of binary synapses

Haiping Huang, Haijun Zhou

摘要:

二元突触网络中的学习是一个NP完全问题。构造了突触权重空间中的组合随机局部搜索策略,进一步提高了单个随机步行器的学习性能。我们应用两个相关的随机游走器,由它们的汉明距离和相关的能量成本(未学习的模式的数量)来学习相同的大模式集。每个步行者首先学习整个模式集的一小部分(两个步行者部分不同,但具有相同数量的模式),然后两个步行者合作探索各自的权重空间,以找到正确分类整个模式集的解决方案。所需的解决方案位于这两个步行者探索的重量空间的公共部分。这种组合策略的效率是支持我们广泛的数值模拟和典型的汉明距离以及能源成本估计退火计算。

英文摘要:

Learning in networks of binary synapses is known to be an NP-complete problem. A combined stochastic local search strategy in the synaptic weight space is constructed to further improve the learning performance of a single random walker. We apply two correlated random walkers guided by their Hamming distance and associated energy costs (the number of unlearned patterns) to learn a same large set of patterns. Each walker first learns a small part of the whole pattern set (partially different for both walkers but with the same amount of patterns) and then both walkers explore their respective weight spaces cooperatively to find a solution to classify the whole pattern set correctly. The desired solutions locate at the common parts of weight spaces explored by these two walkers. The efficiency of this combined strategy is supported by our extensive numerical simulations and the typical Hamming distance as well as energy cost is estimated by an annealed computation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑