Photonic Reservoir Computer with Output Expansion for Unsupervized Parameter Drift Compensation

Pauwels, Jaël; Sande, Guy Van der; Verschaffelt, Guy; Massar, Serge

doi:10.3390/e23080955

Cited by 5 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We note that related techniques for enhancing the reservoir size is also proposed in Refs. [23,[36][37][38].…”

Section: Reservoir Enhancement Techniquesmentioning

confidence: 99%

Short-wavelength Reverberant Wave Systems for Physical Realization of Reservoir Computing

Ma,

Antonsen,

Anlage

et al. 2022

Preprint

View full text Add to dashboard Cite

Machine learning (ML) has found widespread application over a broad range of important tasks. To enhance ML performance, researchers have investigated computational architectures whose physical implementations promise compactness, high-speed execution, physical robustness, and low energy cost. Here, we experimentally demonstrate an approach that uses the high sensitivity of reverberant short wavelength waves for physical realization and enhancement of computational power of a type of ML known as reservoir computing (RC). The potential computation power of RC systems increases with their effective size. We here exploit the intrinsic property of short wavelength reverberant wave sensitivity to perturbations to expand the effective size of the RC system by means of spatial and spectral perturbations. Working in the microwave regime, this scheme is tested experimentally on different ML tasks. Our results indicate the general applicability of reverberant wave-based implementations of RC and of our effective reservoir size expansion techniques.

show abstract

“…We note that related techniques for enhancing the reservoir size is also proposed in Refs. [23,[36][37][38].…”

Section: Reservoir Enhancement Techniquesmentioning

confidence: 99%

Short-wavelength Reverberant Wave Systems for Physical Realization of Reservoir Computing

Ma,

Antonsen,

Anlage

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Design of a low-cost photonic crystal diode for data processing applications in photonic circuits

Surve

Agravat

Ali

et al. 2022

Waves in Random and Complex Media

View full text Add to dashboard Cite

Reducing reservoir computer hyperparameter dependence by external timescale tailoring

Jaurigue,

Lüdge

2024

Neuromorph. Comput. Eng.

View full text Add to dashboard Cite

Task specific hyperparameter tuning in reservoir computing is an open issue, and is of particular relevance for hardware implemented reservoirs. We investigate the influence of directly including externally controllable task specific timescales on the performance and hyperparameter sensitivity of reservoir computing approaches. We show that the need for hyperparameter optimisation can be reduced if timescales of the reservoir are tailored to the specific task. Our results are mainly relevant for temporal tasks requiring memory of past inputs, for example chaotic timeseries prediciton. We consider various methods of including task specific timescales in the reservoir computing approach and demonstrate the universality of our message by looking at both time-multiplexed and spatially multiplexed reservoir computing.

show abstract

Photonic Reservoir Computer with Output Expansion for Unsupervized Parameter Drift Compensation

Cited by 5 publications

References 28 publications

Short-wavelength Reverberant Wave Systems for Physical Realization of Reservoir Computing

Short-wavelength Reverberant Wave Systems for Physical Realization of Reservoir Computing

Design of a low-cost photonic crystal diode for data processing applications in photonic circuits

Reducing reservoir computer hyperparameter dependence by external timescale tailoring

Contact Info

Product

Resources

About