Reservoir computing with a single time-delay autonomous Boolean node

被引：109

作者：

Haynes, Nicholas D. ^{[1
]}

Soriano, Miguel C. ^{[2
]}

Rosin, David P. ^{[1
]}

Fischer, Ingo ^{[2
]}

Gauthier, Daniel J. ^{[1
]}

机构：

[1] Duke Univ, Dept Phys, Durham, NC 27708 USA

[2] IFISC CSIC UIB, Inst Fis Interdisciplinar & Sistemas Complejos, E-07122 Palma De Mallorca, Spain

来源：

PHYSICAL REVIEW E | 2015年 / 91卷 / 02期

基金：

美国国家科学基金会;

关键词：

EQUATIONS; PERFORMANCE; CHAOS;

D O I：

10.1103/PhysRevE.91.020801

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 demonstrate reservoir computing with a physical system using a single autonomous Boolean logic element with time-delay feedback. The system generates a chaotic transient with a window of consistency lasting between 30 and 300 ns, which we show is sufficient for reservoir computing. We then characterize the dependence of computational performance on system parameters to find the best operating point of the reservoir. When the best parameters are chosen, the reservoir is able to classify short input patterns with performance that decreases over time. In particular, we show that four distinct input patterns can be classified for 70 ns, even though the inputs are only provided to the reservoir for 7.5 ns.

引用

页数：5

共 24 条

[1] Information processing using a single dynamical node as complex system [J].