9 March 2016 Towards pattern generation and chaotic series prediction with photonic reservoir computers
Author Affiliations +
Abstract
Reservoir Computing is a bio-inspired computing paradigm for processing time dependent signals that is particularly well suited for analog implementations. Our team has demonstrated several photonic reservoir computers with performance comparable to digital algorithms on a series of benchmark tasks such as channel equalisation and speech recognition. Recently, we showed that our opto-electronic reservoir computer could be trained online with a simple gradient descent algorithm programmed on an FPGA chip. This setup makes it in principle possible to feed the output signal back into the reservoir, and thus highly enrich the dynamics of the system. This will allow to tackle complex prediction tasks in hardware, such as pattern generation and chaotic and financial series prediction, which have so far only been studied in digital implementations. Here we report simulation results of our opto-electronic setup with an FPGA chip and output feedback applied to pattern generation and Mackey-Glass chaotic series prediction. The simulations take into account the major aspects of our experimental setup. We find that pattern generation can be easily implemented on the current setup with very good results. The Mackey-Glass series prediction task is more complex and requires a large reservoir and more elaborate training algorithm. With these adjustments promising result are obtained, and we now know what improvements are needed to match previously reported numerical results. These simulation results will serve as basis of comparison for experiments we will carry out in the coming months.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Piotr Antonik, Michiel Hermans, François Duport, Marc Haelterman, Serge Massar, "Towards pattern generation and chaotic series prediction with photonic reservoir computers", Proc. SPIE 9732, Real-time Measurements, Rogue Events, and Emerging Applications, 97320B (9 March 2016); doi: 10.1117/12.2210948; https://doi.org/10.1117/12.2210948
PROCEEDINGS
12 PAGES


SHARE
RELATED CONTENT

Finite-precision discrete-time neural network data association
Proceedings of SPIE (September 16 1992)
Optical Algebraic Processing Architectures And Algorithms
Proceedings of SPIE (November 27 1984)
Weight discretization paradigm for optical neural networks
Proceedings of SPIE (August 01 1990)
Impact of noise on an optoelectronic neural network
Proceedings of SPIE (September 16 1992)
Simulation software for neural networks
Proceedings of SPIE (August 19 1993)

Back to Top