Online Training of an Opto-Electronic Reservoir Computer

被引：10

作者：

Antonik, Piotr ^{[1
]}

Duport, Francois ^{[2
]}

Smerieri, Anteo ^{[2
]}

Hermans, Michiel ^{[2
]}

Haelterman, Marc ^{[2
]}

Massar, Serge ^{[1
]}

机构：

[1] Univ Libre Bruxelles, Lab Informat Quant, 50 Ave FD Roosevelt,CP 225, B-1050 Brussels, Belgium

[2] Univ Libre Bruxelles, Serv OPERA Photon, B-1050 Brussels, Belgium

来源：

NEURAL INFORMATION PROCESSING, PT II | 2015年 / 9490卷

关键词：

D O I：

10.1007/978-3-319-26535-3_27

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 bio-inspired computing paradigm for processing time dependent signals. Its analog implementations equal and sometimes outperform other digital algorithms on a series of benchmark tasks. Their performance can be increased by switching from offline to online training method. Here we present the first online trained optoelectronic reservoir computer. The system is tested on a channel equalisation task and the algorithm is executed by an FPGA chip. We report performances close to previous implementations and demonstrate the benefits of online training on a non-stationary task that could not be easily solved using offline methods.

引用

页码：233 / 240

页数：8