Delay-Based Reservoir Computing: Noise Effects in a Combined Analog and Digital Implementation

被引：128

作者：

Soriano, Miguel C. ^{[1
]}

Ortin, Silvia ^{[2
]}

Keuninckx, Lars ^{[3
]}

Appeltant, Lennert ^{[3
]}

Danckaert, Jan ^{[3
]}

Pesquera, Luis ^{[2
]}

Van der Sande, Guy ^{[3
]}

机构：

[1] IFISC, E-07122 Palma De Mallorca, Spain

[2] IFCA, Inst Fis Cantabria, E-39005 Santander, Spain

[3] Vrije Univ Brussel, Appl Phys Res Grp, B-1050 Brussels, Belgium

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS | 2015年 / 26卷 / 02期

关键词：

Delay systems; dynamical systems; electronic circuits; memory capacity; pattern recognition; reservoir computing (RC); time-series prediction; NEURAL-NETWORKS;

D O I：

10.1109/TNNLS.2014.2311855

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Reservoir computing is a paradigm in machine learning whose processing capabilities rely on the dynamical behavior of recurrent neural networks. We present a mixed analog and digital implementation of this concept with a nonlinear analog electronic circuit as a main computational unit. In our approach, the reservoir network can be replaced by a single nonlinear element with delay via time-multiplexing. We analyze the influence of noise on the performance of the system for two benchmark tasks: 1) a classification problem and 2) a chaotic time-series prediction task. Special attention is given to the role of quantization noise, which is studied by varying the resolution in the conversion interface between the analog and digital worlds.

引用

页码：388 / 393

页数：6

共 25 条

[1]

[Anonymous], 1991, TEX INSTR DEV 46 WOR

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