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 …

Photonic neuromorphic technologies in optical communications

A Argyris - Nanophotonics, 2022‏ - degruyter.com
Abstract Machine learning (ML) and neuromorphic computing have been enforcing problem-
solving in many applications. Such approaches found fertile ground in optical …

Deep photonic reservoir computing recurrent network

YW Shen, RQ Li, GT Liu, J Yu, X He, L Yi, C Wang - Optica, 2023‏ - opg.optica.org
Deep neural networks usually process information through multiple hidden layers. However,
most hardware reservoir computing recurrent networks only have one hidden reservoir …

Parallel and deep reservoir computing using semiconductor lasers with optical feedback

H Hasegawa, K Kanno, A Uchida - Nanophotonics, 2023‏ - degruyter.com
Photonic reservoir computing has been intensively investigated to solve machine learning
tasks effectively. A simple learning procedure of output weights is used for reservoir …

Deriving task specific performance from the information processing capacity of a reservoir computer

T Hülser, F Köster, K Lüdge, L Jaurigue - Nanophotonics, 2023‏ - degruyter.com
In the reservoir computing literature, the information processing capacity is frequently used
to characterize the computing capabilities of a reservoir. However, it remains unclear how …

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 …

Photonic deep residual time-delay reservoir computing

C Zhou, Y Huang, Y Yang, D Cai, P Zhou, N Li - Neural Networks, 2024‏ - Elsevier
Time-delay reservoir computing (TDRC) represents a simplified variant of recurrent neural
networks, employing a nonlinear node with a feedback mechanism to construct virtual …

Hybrid parallel photonic reservoir computing with accelerated data processing speed

L Zhang, L Peng, S Li, W Pan, L Jiang, L Yan… - Optics & Laser …, 2024‏ - Elsevier
Reservoir computing is a bio-inspired approach especially suited for processing time-
dependent information. In this work, we propose a hybrid reservoir computing scheme …

Secure communication via chaotic synchronization based on reservoir computing

J Liu, J Zhang, Y Wang - IEEE Transactions on Neural …, 2022‏ - ieeexplore.ieee.org
Information security occupies a very important part of national security. Chaos
communication can provide high-level physical layer security, but its harsh claims on the …

Asynchronous photonic time-delay reservoir computing

JY Tang, BD Lin, YW Shen, RQ Li, J Yu, X He… - Optics …, 2023‏ - opg.optica.org
Time-delay reservoir computing uses a nonlinear node associated with a feedback loop to
construct a large number of virtual neurons in the neural network. The clock cycle of the …