Random Pattern and Frequency Generation Using a Photonic Reservoir Computer with Output Feedback
- 192 Downloads
Reservoir computing is a bio-inspired computing paradigm for processing time dependent signals. The performance of its analogue implementations matches other digital algorithms on a series of benchmark tasks. Their potential can be further increased by feeding the output signal back into the reservoir, which would allow to apply the algorithm to time series generation. This requires, in principle, implementing a sufficiently fast readout layer for real-time output computation. Here we achieve this with a digital output layer driven by a FPGA chip. We demonstrate the first opto-electronic reservoir computer with output feedback and test it on two examples of time series generation tasks: frequency and random pattern generation. We obtain very good results on the first task, similar to idealised numerical simulations. The performance on the second one, however, suffers from the experimental noise. We illustrate this point with a detailed investigation of the consequences of noise on the performance of a physical reservoir computer with output feedback. Our work thus opens new possible applications for analogue reservoir computing and brings new insights on the impact of noise on the output feedback.
KeywordsReservoir computing Opto-electronic setup Time series generation FPGA Output feedback
This study was funded by the Interuniversity Attraction Poles program of the Belgian Science Policy Office (Grant IAP P7-35 “photonics@be”), by the Fonds de la Recherche Scientifique FRS-FNRS and by the Action de Recherche Concertée of the Académie Universitaire Wallonie-Bruxelles (Grant AUWB-2012-12/17-ULB9).
Compliance with Ethical Standards
Conflict of interest
All authors declare that they have no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
- 1.The 2006/07 forecasting competition for neural networks & computational intelligence. http://www.neural-forecasting-competition.com/NN3/ (2006)
- 2.Aldridge I (2009) High-frequency trading: a practical guide to algorithmic strategies and trading systems. Wiley, HobokenGoogle Scholar
- 3.Antonik P, Duport F, Hermans M, Smerieri A, Haelterman M, Massar S (2016) Online training of an opto-electronic reservoir computer applied to real-time channel equalization. IEEE Trans Neural Netw Learn Syst PP(99):1–13Google Scholar
- 4.Antonik P, Haelterman M, Massar S (2017) Online training for high-performance analogue readout layers in photonic reservoir computers. Cognit Comput. doi: 10.1007/s12559-017-9459-3
- 5.Antonik P, Hermans M, Duport F, Haelterman M, Massar S (2016) Towards pattern generation and chaotic series prediction with photonic reservoir computers. In: SPIE’s 2016 Laser Technology and Industrial Laser Conference, vol. 9732, p 97320BGoogle Scholar
- 6.Antonik P, Hermans M, Haelterman M, Massar S (2016) Pattern and frequency generation using an opto-electronic reservoir computer with output feedback. In: APNNS’s 23th international conference on neural information processing, LNCS, vol. 9948, pp 318–325Google Scholar
- 7.Antonik P, Hermans M, Haelterman M, Massar S (2016) Towards adjustable signal generation with photonic reservoir computers. In: 25th international conference on artificial neural networks, vol. 9886Google Scholar
- 9.Arsenault H (2012) Optical processing and computing. Elsevier, AmsterdamGoogle Scholar
- 14.Jaeger H (2001) Short term memory in echo state networks. Technical GMD Report, vol 152Google Scholar
- 24.Smerieri A, Duport F, Paquot Y, Schrauwen B, Haelterman M, Massar S (2012) Analog readout for optical reservoir computers. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ (eds) Advances in neural information processing systems 25 (NIPS2012). Curran Associates, Inc., pp 944–952. https://papers.nips.cc/paper/4718-analog-readout-for-optical-reservoir-computers.pdf
- 27.Triefenbach F, Jalalvand A, Schrauwen B, Martens JP (2010) Phoneme recognition with large hierarchical reservoirs. Adv Neural Inf Process Syst 23:2307–2315Google Scholar
- 29.Vinckier Q, Bouwens A, Haelterman M, Massar S (2016) Autonomous all-photonic processor based on reservoir computing paradigm. p SF1F.1. Optical Society of AmericaGoogle Scholar
- 32.Wyffels F, Schrauwen B, Stroobandt D (2008) Stable output feedback in reservoir computing using ridge regression. In: International conference on artificial neural networks, pp 808–817. Springer, BerlinGoogle Scholar