arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1409.0227cond-mat.dis-nn
收藏

分层神经网络执行串行和并行处理

Hierarchical neural networks perform both serial and parallel processing

Elena Agliari, Adriano Barra, Andrea Galluzzi, Francesco Guerra, Daniele Tantari, Flavia Tavani

摘要:

在这项工作中,我们研究了一个赫布神经网络,神经元排列根据一个层次结构,使他们的耦合规模与他们的倒数距离。由于完整的统计力学解决方案还不可用,因此在通过该途径对现有技术进行流线型介绍之后,通过信噪比技术和广泛的数值模拟始终接近该问题。专注于低存储制度,其中存储的模式的数量增长与系统的大小最几何,我们证明了这些非平均场Hopfield网络显示出比他们的经典同行更丰富的相图。特别是,这些网络能够执行串行处理(即通过整个神经元集合的完全重新排列一次检索一个模式)以及并行处理(即同时检索几个模式,将不同模式的管理委托给构建网络的不同社区)。这两种状态之间的调谐由耦合衰减的速率和影响系统的噪声水平给出。为这些非凡的能力付出的代价在于网络的容量小于平均场对应物,因此产生了一个新的预算原则:多任务处理能力越广泛,网络负载越低,反之亦然。这可能对我们理解生物复杂性有重要意义。

英文摘要:

In this work we study a Hebbian neural network, where neurons are arranged according to a hierarchical architecture such that their couplings scale with their reciprocal distance. As a full statistical mechanics solution is not yet available, after a streamlined introduction to the state of the art via that route, the problem is consistently approached through signal- to-noise technique and extensive numerical simulations. Focusing on the low-storage regime, where the amount of stored patterns grows at most logarithmical with the system size, we prove that these non-mean-field Hopfield-like networks display a richer phase diagram than their classical counterparts. In particular, these networks are able to perform serial processing (i.e. retrieve one pattern at a time through a complete rearrangement of the whole ensemble of neurons) as well as parallel processing (i.e. retrieve several patterns simultaneously, delegating the management of diff erent patterns to diverse communities that build network). The tune between the two regimes is given by the rate of the coupling decay and by the level of noise affecting the system. The price to pay for those remarkable capabilities lies in a network's capacity smaller than the mean field counterpart, thus yielding a new budget principle: the wider the multitasking capabilities, the lower the network load and viceversa. This may have important implications in our understanding of biological complexity.

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。

↑