par Antonik, Piotr 
;Duport, Francois ;Smerieri, Anteo ;Hermans, Michiel ;Haelterman, Marc ;Massar, Serge
Editeur scientifique Arik, S.
Référence International Conference on Neural Information Processing(22: Istanbul, Turkey), Lecture Notes in Computer Science, Springer, Vol. 9490, page (233-240)
Publication Publié, 2015-11-11
;Duport, Francois ;Smerieri, Anteo ;Hermans, Michiel ;Haelterman, Marc ;Massar, Serge Editeur scientifique Arik, S.
Référence International Conference on Neural Information Processing(22: Istanbul, Turkey), Lecture Notes in Computer Science, Springer, Vol. 9490, page (233-240)
Publication Publié, 2015-11-11
Publication dans des actes
| Résumé : | 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 opto-electronic 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. |
