arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1209.5941cond-mat.dis-nn
收藏

稀释感知器学习中副本对称解的稳定性

Stability of the replica symmetric solution in diluted perceptron learning

Alejandro Lage-Castellanos, Andrea Pagnani, Gretel Quintero Angulo

摘要:

我们研究了稀释度在连续耦合感知器模型的平均行为中所起的作用。我们分析了作为稀释场的函数的副本对称解的稳定性的推广和记忆问题。由于加德纳一样的稳定性分析,我们表明,在任何固定的比例$α$之间的模式的数量M和感知器的维数N($α=M/N$),存在一个临界稀释字段$h_c$以上的副本对称animation变得不稳定。

英文摘要:

We study the role played by the dilution in the average behavior of a perceptron model with continuous coupling with the replica method. We analyze the stability of the replica symmetric solution as a function of the dilution field for the generalization and memorization problems. Thanks to a Gardner like stability analysis we show that at any fixed ratio $α$ between the number of patterns M and the dimension N of the perceptron ($α=M/N$), there exists a critical dilution field $h_c$ above which the replica symmetric ansatz becomes unstable.

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。

↑