Results 241 to 250 of about 7,314,717 (264)

Self-learning physical reservoir computer

Physical Review E
A self-learning physical reservoir computer is demonstrated using an adaptive oscillator. Whereas physical reservoir computing repurposes the dynamics of a physical system for computation through machine learning, adaptive oscillators can innately learn and store information in plastic dynamic states.
Md Raf E Ul Shougat, XiaoFu Li, Edmon Perkins   +2 more
openaire   +2 more sources

Physical Reservoir Computing in Robotics

2021
In recent years, there has been an increasing interest in using the concept of physical reservoir computing in robotics. The idea is to employ the robot’s body and its dynamics as a computational resource. On one hand, this has been driven by the introduction of mathematical frameworks showing how complex mechanical structures can be used to build ...
openaire   +1 more source

Physical reservoir computing on a soft bio-inspired swimmer

Neural Networks
Bio-inspired Autonomous Underwater Vehicles with soft bodies provide significant performance benefits over conventional propeller-driven vehicles; however, it is difficult to control these vehicles due to their soft underactuated bodies. This study investigates the application of Physical Reservoir Computing (PRC) in the swimmer's flexible body to ...
Patrick Musgrave
exaly   +4 more sources

Dynamic memristor for physical reservoir computing

Nanoscale
This minireview explores the tunable dynamic properties and potential applications of memristor-based physical reservoir computing.
Qi-Rui Zhang, Wei-Lun Ouyang, Xue-Mei Wang, Fan Yang, Jian-Gang Chen, Zhi-Xing Wen, Jia-Xin Liu, Ge Wang, Qing Liu, Fu-Cai Liu   +9 more
openaire   +2 more sources

Physical reservoir computing with emerging electronics

Nature Electronics
Xiangpeng Liang, Huaqiang Wu, Jianshi Tang   +2 more
exaly   +2 more sources

A current-controlled magnonic reservoir for physical reservoir computing

Applied Physics Letters
Physical reservoir computers based on principles of magnonics promise energy efficient data processing and a reduction in the size and weight of the neuromorphic computing devices. The present work is a major step toward all-magnonic implementation of the recently proposed concept of a physical reservoir based on the spin wave active ring.
Alexey B. Ustinov, Roman V. Haponchyk, Mikhail Kostylev   +2 more
openaire   +1 more source

Physical Reservoir Computing with Electrochemical Reactions

ECS Meeting Abstracts
Machine learning based on neural networks (NN) has been used for information processing.1 However, some disadvantages of NN are the high cost of computational resources and long training process. To overcome these limitations, physical reservoir computing (PRC) was proposed.2 In PRC, signals are fed to PR devices that produce non-linear responses ...
Ryo Yamada, S. Watanabe, T Fukuoka, S Hirooka, H. Inatsu, M. Nakagawa, H Tada   +6 more
openaire   +1 more source

Non-instantaneous Information Transfer in Physical Reservoir Computing

2021
The Echo State Network reservoir computing model is used in many applications. The original equations have a form of ‘instantaneous’ information flow. Here we suggest using a more physically realistic form of the equations, which takes into account the time needed for information to flow and to be processed.
openaire   +1 more source

Tradeoffs with physical delay feedback reservoir computing

2021 IEEE Symposium Series on Computational Intelligence (SSCI), 2021
Tian Gan, Susan Stepney, Martin A. Trefzer   +2 more
openaire   +1 more source

Transferring Reservoir Computing: Formulation and Application to Fluid Physics

2019
We propose a transfer learning for reservoir computing, and verify the effectivity of the proposed methods for the standard inference task of the Lorenz system. Applying the proposed methods to an inference task of fluid physics, we show the inference accuracy is drastically improved compared with the conventional reservoir computing method if ...
Masanobu Inubushi, Susumu Goto
openaire   +2 more sources