Summary
the 2014 International Symposium on Nonlinear Theory and its Applications
2014
Session Number:C2L-E
Session:
Number:C2L-E4
Reservoir computing using consistency of semiconductor lasers with optical feedback and injection
Joma Nakayama, Kazutaka Kanno, Atsushi Uchida,
pp.557-560
Publication Date:2014/9/14
Online ISSN:2188-5079
Summary:
Reservoir computing is a novel bio-inspired computing method and highly efficient approach for processing empirical data. One of the important properties of reservoir computing is consistency, where the same response output can be observed by a repeated drive signal. Semiconductor lasers with optical injection show consistent outputs. We implement reservoir computing by using semiconductor lasers subject to optical delayed-feedback and injection. We investigate the performance on Santa Fe laser time-series prediction task.