Role of delay-times in delay-based photonic reservoir computing

T Hülser, F Köster, L Jaurigue, K Lüdge - Optical Materials Express, 2022‏ - opg.optica.org
Delay-based reservoir computing has gained a lot of attention due to the relative simplicity
with which this concept can be implemented in hardware. However, unnecessary constraints …

Theory of neuromorphic computing by waves: machine learning by rogue waves, dispersive shocks, and solitons

G Marcucci, D Pierangeli, C Conti - Physical Review Letters, 2020‏ - APS
We study artificial neural networks with nonlinear waves as a computing reservoir. We
discuss universality and the conditions to learn a dataset in terms of output channels and …

Irreversibility, heat and information flows induced by non-reciprocal interactions

SAM Loos, SHL Klapp - New Journal of Physics, 2020‏ - iopscience.iop.org
We study the thermodynamic properties induced by non-reciprocal interactions between
stochastic degrees of freedom in time-and space-continuous systems. We show that, under …

Photonic extreme learning machine by free-space optical propagation

D Pierangeli, G Marcucci, C Conti - Photonics Research, 2021‏ - opg.optica.org
Photonic brain-inspired platforms are emerging as novel analog computing devices,
enabling fast and energy-efficient operations for machine learning. These artificial neural …

Networks of random lasers: current perspective and future challenges

A Consoli, N Caselli, C López - Optical Materials Express, 2023‏ - opg.optica.org
Artificial neural networks are widely used in many different applications because of their
ability to deal with a range of complex problems generally involving massive data sets …

Reducing reservoir computer hyperparameter dependence by external timescale tailoring

L Jaurigue, K Lüdge - Neuromorphic Computing and Engineering, 2024‏ - iopscience.iop.org
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 …

[HTML][HTML] Reservoir computing with delayed input for fast and easy optimisation

L Jaurigue, E Robertson, J Wolters, K Lüdge - Entropy, 2021‏ - mdpi.com
Reservoir computing is a machine learning method that solves tasks using the response of a
dynamical system to a certain input. As the training scheme only involves optimising the …

Chaotic attractor reconstruction using small reservoirs—the influence of topology

L Jaurigue - Machine Learning: Science and Technology, 2024‏ - iopscience.iop.org
Forecasting timeseries based upon measured data is needed in a wide range of
applications and has been the subject of extensive research. A particularly challenging task …

Large-scale photonic natural language processing

C M. Valensise, I Grecco, D Pierangeli… - Photonics Research, 2022‏ - opg.optica.org
Modern machine-learning applications require huge artificial networks demanding
computational power and memory. Light-based platforms promise ultrafast and energy …

All-optical spiking neuron based on passive microresonator

J **ang, A Torchy, X Guo, Y Su - Journal of Lightwave …, 2020‏ - ieeexplore.ieee.org
Neuromorphic photonics that aims to process and store information simultaneously like
human brains has emerged as a promising alternative for next generation intelligent …