arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1101.4351cs.AIcs.CRmath.DSmath.GN
收藏

构造一个混沌证明的神经网络

Building a Chaotic Proved Neural Network

University of Franche-Comté(弗朗什-孔泰大学);IUT de Belfort-Montbéliard(贝尔福-蒙贝利亚尔大学技术学院)

Jacques M. Bahi, Christophe Guyeux, Michel Salomon

摘要:

混沌神经网络近年来受到了广泛的关注。在本文中,我们建立了一个精确的对应关系之间的所谓的混沌迭代和一类特殊的人工神经网络:全局递归多层感知器。我们正式表明,这是可能的,使这些迭代行为混乱,定义Devaney,因此,我们得到了第一个神经网络证明混沌。几个具有不同结构的神经网络被训练成表现出混沌行为。

英文摘要:

Chaotic neural networks have received a great deal of attention these last years. In this paper we establish a precise correspondence between the so-called chaotic iterations and a particular class of artificial neural networks: global recurrent multi-layer perceptrons. We show formally that it is possible to make these iterations behave chaotically, as defined by Devaney, and thus we obtain the first neural networks proven chaotic. Several neural networks with different architectures are trained to exhibit a chaotical behavior.

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。

↑