Finding the Proper Input Masking for Improving the Performance of Optical Reservoir Computers

Please enable javascript in your browser.

Hemmatyar, Omid | 2018

520 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 50799 (05)
University: Sharif University of Technology
Department: Electrical Engineering
Advisor(s): Mehrany, Khashayar
Abstract:
Reservoir Computing is a novel computing paradigm that uses a nonlinear recurrent dynamical system to carry out information processing. Recent electronic and optoelectronic Reservoir Computers based on an architecture with a single nonlinear node and a delay loop have shown performance on standardized tasks comparable to state-of-the-art digital implementations. Here we report an all-optical implementation of a Reservoir Computer, made of off-the-shelf components for optical telecommunications. It uses a semiconductor optical amplifier as nonlinearity, and a Fabry-Perot Resonator as a key element to establish the virtual nodes, connecting them and consequently, build the virtual neural vetwork. The present work shows that, within the Reservoir Computing paradigm, all-optical computing with state-of-the-art performance is possible
Keywords:
Machine Learning ; Recurrent Neural Networks ; Optical Reservoir Computing ; Optical Signal Processing ; Dynamical Systems with Delayed Feedback

No TOC