Learning and generation of long-range correlated sequences

被引:1
|
作者
Priel, A [1 ]
Kanter, I
机构
[1] Bar Ilan Univ, Minerva Ctr, IL-52900 Ramat Gan, Israel
[2] Bar Ilan Univ, Dept Phys, IL-52900 Ramat Gan, Israel
来源
PHYSICAL REVIEW E | 2000年 / 62卷 / 02期
关键词
D O I
10.1103/PhysRevE.62.1617
中图分类号
O35 [流体力学]; O53 [等离子体物理学];
学科分类号
070204 ; 080103 ; 080704 ;
摘要
We study the capability to learn and to generate long-range, power-law correlated sequences by a fully connected asymmetric network. The focus is set on the ability of neural networks to extract statistical features from a sequence. We demonstrate that the average power-law behavior is learnable, namely, the sequence generated by the trained network obeys the same statistical behavior. The interplay between a correlated weight matrix and the sequence generated by such a network is explored. A weight matrix with a power-law correlation function along the vertical direction, gives rise to a sequence with a similar statistical behavior.
引用
收藏
页码:1617 / 1621
页数:5
相关论文
empty
未找到相关数据