Towards Adjustable Signal Generation with Photonic Reservoir Computers

被引：1

作者：

Antonik, Piotr ^{[1
]}

Hermans, Michiel ^{[1
]}

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, 50 Ave FD Roosevelt,CP 194-5, B-1050 Brussels, Belgium

来源：

ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2016, PT I | 2016年 / 9886卷

关键词：

Reservoir Computing; FPGA; Pattern generation; Numerical results; Opto-electronic systems;

D O I：

10.1007/978-3-319-44778-0_44

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. We have recently reported the first opto-electronic reservoir computer trained online by an FPGA chip. This setup makes it in principle possible to feed the output signal back into the reservoir, which in turn allows to tackle complex prediction tasks in hardware. In present work, we investigate numerically the performance of an offline-trained opto-electronic reservoir computer with output feedback on four signal generation tasks. We report very good results and show the potential of such setup to be used as a high-speed analog control system.

引用

页码：374 / 381

页数：8

共 21 条

[1]

[Anonymous], 2006, 2006 07 FORECASTING

[2]

Antonik P., 2016, SPIES 2016 LAS TECHN, V9732

[3] Online Training of an Opto-Electronic Reservoir Computer [J].

Antonik, Piotr ;

Duport, Francois ;

Smerieri, Anteo ;

Hermans, Michiel ;

Haelterman, Marc ;

Massar, Serge .

NEURAL INFORMATION PROCESSING, PT II, 2015, 9490 :233-240

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

Appeltant, L. ;

Soriano, M. C. ;

Van der Sande, G. ;

Danckaert, J. ;

Massar, S. ;

Dambre, J. ;

Schrauwen, B. ;

Mirasso, C. R. ;

Fischer, I. .

NATURE COMMUNICATIONS, 2011, 2

[5] Parallel photonic information processing at gigabyte per second data rates using transient states [J].

Brunner, Daniel ;

Soriano, Miguel C. ;

Mirasso, Claudio R. ;

Fischer, Ingo .

NATURE COMMUNICATIONS, 2013, 4

[6] All-optical reservoir computing [J].

Duport, Francois ;

Schneider, Bendix ;

Smerieri, Anteo ;

Haelterman, Marc ;

Massar, Serge .

OPTICS EXPRESS, 2012, 20 (20) :22783-22795

[7]

Hammer B., 2009, P EUR S ART NEUR NET, P213

[8] Reservoir computing with a single time-delay autonomous Boolean node [J].

Haynes, Nicholas D. ;

Soriano, Miguel C. ;

Rosin, David P. ;

Fischer, Ingo ;

Gauthier, Daniel J. .

PHYSICAL REVIEW E, 2015, 91 (02)

[9] Central pattern generators for locomotion control in animals and robots: A review [J].

Ijspeert, Auke Jan .

NEURAL NETWORKS, 2008, 21 (04) :642-653

[10] Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication [J].

Jaeger, H ;

Haas, H .

SCIENCE, 2004, 304 (5667) :78-80

← 1 2 3 →