arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0911.3096cond-mat.dis-nncond-mat.stat-mech
收藏

类比神经网络的副本对称性

The replica symmetric behavior of the analogical neural network

Adriano Barra, Giuseppe Genovese, Francesco Guerra

摘要:

在本文中,我们继续我们的调查的类比神经网络,支付利息的副本对称行为的情况下,任何类型的外部领域。桥接的神经网络的二分自旋玻璃,我们引入并应用一个新的插值方案,其自由能,自然扩展通过腔场或随机扰动这些模型的插值。作为结果,我们得到的自由能的系统作为一个总和规则,其中,至少在副本对称水平,可以准确地解决。作为下一步,我们研究其相关的自洽方程的序参量和他们的重新标度的波动,发现分歧的标准Amit Gutfreund Sompolinsky理论的同一临界线。

英文摘要:

In this paper we continue our investigation of the analogical neural network, paying interest to its replica symmetric behavior in the absence of external fields of any type. Bridging the neural network to a bipartite spin-glass, we introduce and apply a new interpolation scheme to its free energy that naturally extends the interpolation via cavity fields or stochastic perturbations to these models. As a result we obtain the free energy of the system as a sum rule, which, at least at the replica symmetric level, can be solved exactly. As a next step we study its related self-consistent equations for the order parameters and their rescaled fluctuations, found to diverge on the same critical line of the standard Amit-Gutfreund-Sompolinsky theory.

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。

↑