Photonic delay systems as machine learning implementations

Nonlinear photonic delay systems present interesting implementation platforms for machine learning models. They can be extremely fast, offer great degrees of parallelism and potentially consume far less power than digital processors. So far they have been successfully employed for signal processing using the Reservoir Computing paradigm. In this paper we show that their range of applicability can be greatly extended if we use gradient descent with backpropagation through time on a model of the system to optimize the input encoding of such systems. We perform physical experiments that demonstrate that the obtained input encodings work well in reality, and we show that optimized systems perform significantly better than the common Reservoir Computing approach. The results presented here demonstrate that common gradient descent techniques from machine learning may well be applicable on physical neuro-inspired analog computers. ∗OPERA Photonique, Universit/’e Libre de Bruxelles, Avenue F. Roosevelt 50, 1050 Brussels ([email protected]) †Instituto de F́ısica Interdisciplinar y Sistemas Complejos, IFISC (UIB-CSIC), Campus Universitat de les Illes Balears, E-07122 Palma de Mallorca, Spain ‡ELIS departement, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent, Belgium §INTEC departement, Ghent University, Sint Pietersnieuwstraat 41, 9000 Ghent, Belgium ¶Instituto de F́ısica Interdisciplinar y Sistemas Complejos, IFISC (UIB-CSIC), Campus Universitat de les Illes Balears, E-07122 Palma de Mallorca, Spain 1 ar X iv :1 50 1. 02 59 2v 1 [ cs .N E ] 1 2 Ja n 20 15