Conditions for reservoir computing performance using semiconductor lasers with delayed optical feedback

Bueno, Julián; Brunner, Daniel; Soriano, Miguel C.; Fischer, Ingo

doi:10.1364/oe.25.002401

Cited by 179 publications

(110 citation statements)

References 39 publications

Supporting

Mentioning

104

Contrasting

Order By: Relevance

“…The optimal operation conditions for an all-optical feedback loop system were experimentally investigated in (Bueno et al, 2017). The effects of detuning of the frequency between an injection laser and the reservoir laser as well as the locking of the laser state were studied for a chaotic time series prediction task.…”

Section: Optical Feedback In a Laser Cavitymentioning

confidence: 99%

Recent advances in physical reservoir computing: A review

et al. 2019

View full text Add to dashboard Cite

Reservoir computing is a computational framework suited for temporal/sequential data processing. It is derived from several recurrent neural network models, including echo state networks and liquid state machines. A reservoir computing system consists of a reservoir for mapping inputs into a high-dimensional space and a readout for pattern analysis from the high-dimensional states in the reservoir. The reservoir is fixed and only the readout is trained with a simple method such as linear regression and classification. Thus, the major advantage of reservoir computing compared to other recurrent neural networks is fast learning, resulting in low training cost. Another advantage is that the reservoir without adaptive updating is amenable to hardware implementation using a variety of physical systems, substrates, and devices. In fact, such physical reservoir computing has attracted increasing attention in diverse fields of research. The purpose of this review is to provide an overview of recent advances in physical reservoir computing by classifying them according to the type of the reservoir. We discuss the current issues and perspectives related to physical reservoir computing, in order to further expand its practical applications and develop next-generation machine learning systems.

show abstract

Section: Optical Feedback In a Laser Cavitymentioning

confidence: 99%

Recent advances in physical reservoir computing: A review

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The injected signal u(n + 1) is the chaotic Mackey-Glass (MG) sequence [3], and the RNN's learning target is y T (n + 1) = u(n + 2), the onetime-step-prediction of the MG system. Parameters of the temporal MG sequence where identical to [15], using an integration step size of 0.1. For determining the error ε k we discarded the first 30 data points due to their transient nature.…”

Section: Photonic Learningmentioning

confidence: 99%

Reinforcement learning in a large-scale photonic recurrent neural network

Bueno¹,

Maktoobi²,

Froehly³

et al. 2018

Optica

333

207

View full text Add to dashboard Cite

Photonic Neural Network implementations have been gaining considerable attention as a potentially disruptive future technology. Demonstrating learning in large scale neural networks is essential to establish photonic machine learning substrates as viable information processing systems. Realizing photonic Neural Networks with numerous nonlinear nodes in a fully parallel and efficient learning hardware was lacking so far. We demonstrate a network of up to 2500 diffractively coupled photonic nodes, forming a large scale Recurrent Neural Network. Using a Digital Micro Mirror Device, we realize reinforcement learning. Our scheme is fully parallel, and the passive weights maximize energy efficiency and bandwidth. The computational output efficiently converges and we achieve very good performance.

show abstract

“…4b, BER HD-FEC , white dashed line). For the partial locking conditions, the SNR of the reservoir output signal is sufficient for the classification task, while the reservoir memory is maximized, as found in [38]. The temporal characteristics of the transient responses used for the reservoir computation affect the training performance.…”

Section: Resultsmentioning

confidence: 99%

PAM-4 Transmission at 1550 nm Using Photonic Reservoir Computing Post-Processing

2019

Self Cite

View full text Add to dashboard Cite

The efficacy of data decoding in contemporary ultrafast fiber transmission systems is greatly determined by the capabilities of the signal processing tools that are used. The received signal must not exceed a certain level of complexity, beyond which the applied signal processing solutions become insufficient or slow. Moreover, the required signal-to-noise ratio of the received signal can be challenging, especially when adopting modulation formats with multi-level encoding. Lately, photonic reservoir computing (RC) -a hardware machine learning technique with recurrent connectivity -has been proposed as a post-processing tool that deals with deterministic distortions from fiber transmission. Here we show that RC post-processing is remarkably efficient for multilevel encoding and for the use of very high launched optical peak power for fiber transmission up to 14dBm. Higher power levels provide the desired high signal-to-noise ratio (SNR) values at the receiver end, at the expense of a complex nonlinear transformation of the transmission signal. Our demonstration evaluates a direct fiber communication link with 4-level pulse amplitude modulation (PAM-4) encoding and direct detection, without including optical amplification, dispersion compensation, pulse shaping or other digital signal processing (DSP) techniques. By applying RC post-processing on the distorted signal, we numerically estimate fiber transmission distances of 27km at 56Gb/s and of 5.5 km at 112Gb/s data encoding rates, while fulfilling the harddecision forward error correction (HD-FEC) bit-error-rate (BER) limit for data recovery. In an experimental equivalent demonstration of our photonic reservoir, the achieved distances are 21km and 4.6km respectively. he joined the Institute for Cross-Disciplinary Physics and Complex Systems -IFISC (CSIC-UIB) in Spain as a Marie-Skłodowska Curie Fellow. He has participated in 12 research projects, funded by the European Union and the national Greek / Spanish research authorities. He has published more than 80 papers in peer-reviewed journals and conference proceedings, while he is the main author of 3 book chapters. His research interests include nonlinear dynamics in semiconductor lasers, photonic devices and coupled systems, optical communication systems, chaotic encryption, optical sensing and machine learning techniques.

show abstract

Conditions for reservoir computing performance using semiconductor lasers with delayed optical feedback

Cited by 179 publications

References 39 publications

Recent advances in physical reservoir computing: A review

Recent advances in physical reservoir computing: A review

Reinforcement learning in a large-scale photonic recurrent neural network

PAM-4 Transmission at 1550 nm Using Photonic Reservoir Computing Post-Processing

Contact Info

Product

Resources

About