Dresden 2020 – wissenschaftliches Programm
Die DPG-Frühjahrstagung in Dresden musste abgesagt werden! Lesen Sie mehr ...
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
SYNC: Symposium Advanced neuromorphic computing hardware: Towards efficient machine learning
SYNC 1: Advanced neuromorphic computing hardware: Towards efficient machine learning
SYNC 1.1: Hauptvortrag
Montag, 16. März 2020, 09:30–10:00, HSZ 01
Photonic Reservoir Computing and its Application to Optical Communication — •Ingo Fischer and Apostolos Argyris — Instituto de Física Interdisciplinar y Sistemas Complejos IFISC (CSIC-UIB), Campus Universitat de les Illes Balears, E-07122 Palma de Mallorca, Spain
Neuromorphic computing and its analog implementation in specific hardware has been gaining a significant revived interest in recent years. Photonic hardware and reservoir computing as method have found particular interest, due to their potential for ultra-fast and energy-efficient performance and possible photonic integration. In this talk, we present photonic reservoir computing platforms based on semiconductor lasers as nonlinear nodes. We discuss, how their high dynamical bandwidth and compatibility with optical fiber communication hardware make them attractive for signal recovery in optical communications. Presenting experimental and simulation results we demonstrate that state-of-the art performance can be achieved for different modulation schemes.