• Corpus ID: 16788487

Parallel photonic reservoir computing using frequency multiplexing of neurons

  title={Parallel photonic reservoir computing using frequency multiplexing of neurons},
  author={Akram Akrout and Arno Bouwens and François Duport and Quentin Vinckier and Marc Haelterman and Serge Massar},
Today's unrelenting increase in demand for information processing creates the need for novel computing concepts. Reservoir computing is such a concept that lends itself particularly well to photonic hardware implementations. Over recent years, these hardware implementations have gained maturity and now achieve state-of-the-art performance on several benchmark tasks. However, implementations so far are essentially all based on sequential data processing, leaving the inherent parallelism of… 

Figures and Tables from this paper

Towards integrated parallel photonic reservoir computing based on frequency multiplexing

Simulation results show that the laser phase noise is far more important that other types of noise, hence the laser source design/operation should be optimized to achieve low phase noise comb.

Towards autonomous photonic reservoir computer based on frequency parallelism of neurons

The proposed setup is an important step towards analog, low footprint, all-optical information processing, and parallel processing will be necessary for high bandwidth applications.

Parallel photonic reservoir computing based on frequency multiplexing of neurons

A parallel implementation of reservoir computing that uses frequency domain multiplexing of neuron states, with the potential of significantly reducing the computation time compared to sequential architectures is reported.

Photonic reservoir computer based on frequency multiplexing.

A photonic implementation of a reservoir computer that exploits frequency domain multiplexing to encode neuron states and it is demonstrated that frequency multiplexed allows output weights to be implemented in the optical domain, through optical attenuation.

Bayesian optimisation of large-scale photonic reservoir computers

This work proposes the use of Bayesian optimisation for efficient exploration of the hyper-parameter space in a minimum number of iteration, and reports notable improvements in performance and the number of experimental iterations required to optimise thehyper-parameters of the photonic reservoir computing system.

Dual time- and wavelength-multiplexed photonic reservoir computing

Progress is discussed in developing a next-generation photonic reservoir with dual time and wavelength multiplexing, which allows for a reservoir with increased size and complexity, enabling it to successfully perform complex classification and prediction tasks.

Using multidimensional speckle dynamics for high-speed, large-scale, parallel photonic computing

The use of multidimensional speckle dynamics in multimode fibers for information processing, where input information is mapped into the space, frequency, and time domains by an optical phase modulation technique, offers a novel approach toward realizing parallel, high-speed, and large-scale photonic computing.

Novel frontier of photonics for data processing—Photonic accelerator

The bottleneck and the paradigm shift of digital computing are reviewed and an array of PAXEL architectures and applications are reviewed, including artificial neural networks, reservoir computing, pass-gate logic, decision making, and compressed sensing are reviewed.

Recent Advances in Physical Reservoir Computing: A Review

Human action recognition with a large-scale brain-inspired photonic computer

A reservoir computer that recognizes different forms of human action from video streams using photonic neural networks, comparable to state-of-the-art digital implementations, while promising a higher processing speed in comparison to the existing hardware approaches.



Parallel Reservoir Computing Using Optical Amplifiers

This paper uses an isolated word recognition task with babble noise to evaluate the performance of the photonic reservoirs with respect to traditional software reservoir implementations, and shows that the use of coherent light in a well-tuned reservoir architecture offers significant performance benefits.

High performance photonic reservoir computer based on a coherently driven passive cavity

The present experiment, given its good performances, low energy consumption and conceptual simplicity, confirms the great potential of photonic reservoir computing for information processing applications ranging from artificial intelligence to telecommunications.

Experimental demonstration of reservoir computing on a silicon photonics chip.

This work proposes the first integrated passive silicon photonics reservoir and demonstrates that this generic chip can be used to perform arbitrary Boolean logic operations with memory as well as 5-bit header recognition up to 12.5 Gbit s(-1), without power consumption in the reservoir.

Parallel photonic information processing at gigabyte per second data rates using transient states

The potential of a simple photonic architecture to process information at unprecedented data rates is demonstrated, implementing a learning-based approach and all digits with very low classification errors are identified and chaotic time-series prediction with 10% error is performed.

Toward optical signal processing using photonic reservoir computing.

Although they differ in many key respects from traditional software-based hyperbolic tangent reservoirs, it is shown using simulations that such a photonic reservoir can outperform traditional reservoirs on a benchmark classification task.

Nanophotonic Reservoir Computing With Photonic Crystal Cavities to Generate Periodic Patterns

A novel optical architecture based on nanophotonic crystal cavities is introduced, which allows us to integrate many neurons on one chip, which, compared with other photonic solutions, closest resembles a classical neural network.

Photonic information processing beyond Turing: an optoelectronic implementation of reservoir computing.

This work experimentally demonstrate optical information processing using a nonlinear optoelectronic oscillator subject to delayed feedback and implements a neuro-inspired concept, called Reservoir Computing, proven to possess universal computational capabilities.

All-optical Reservoir Computing

An all-optical implementation of a Reservoir Computer, made of off-the-shelf components for optical telecommunications, using the saturation of a semiconductor optical amplifier as nonlinearity is reported.

Optoelectronic Reservoir Computing

This work reports an optoelectronic implementation of reservoir computing based on a recently proposed architecture consisting of a single non linear node and a delay line that is sufficiently fast for real time information processing.

All-optical reservoir computer based on saturation of absorption.

This work proposes here the first reservoir computer based on a fully passive nonlinearity, namely the saturable absorption of a semiconductor mirror, which constitutes an important step towards the development of ultrafast low-consumption analog computers.