arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.03577cond-mat.dis-nn
收藏

非对称神经网络的可满足性转移

Satisfiability transition in asymmetric neural networks

Fabián Aguirre-López, Mauro Pastore, Silvio Franz

摘要:

神经元之间突触相互作用的不对称性在决定递归神经网络的记忆存储和检索特性方面起着至关重要的作用。在这项工作中,我们分析了存储随机记忆的神经元网络连接的突触矩阵具有一定程度的不对称性的问题。我们研究了相应的可满足性和聚类转换的空间中的约束满足问题的解决方案与寻找突触矩阵给定的记忆。我们发现,除了通常的SAT/UNSAT过渡在一个临界数量的存储在网络中,一个额外的过渡非常不对称的矩阵,其中竞争的约束(明确的不对称与存储)诱导足够的挫折,使它不可能解决的问题。这一发现在存储单个存储器的情况下特别引人注目,其中系统中不存在淬火无序。

英文摘要:

Asymmetry in the synaptic interactions between neurons plays a crucial role in determining the memory storage and retrieval properties of recurrent neural networks. In this work, we analyze the problem of storing random memories in a network of neurons connected by a synaptic matrix with a definite degree of asymmetry. We study the corresponding satisfiability and clustering transitions in the space of solutions of the constraint satisfaction problem associated with finding synaptic matrices given the memories. We find, besides the usual SAT/UNSAT transition at a critical number of memories to store in the network, an additional transition for very asymmetric matrices, where the competing constraints (definite asymmetry vs. memories storage) induce enough frustration in the problem to make it impossible to solve. This finding is particularly striking in the case of a single memory to store, where no quenched disorder is present in the system.

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。

↑