Results 11 to 20 of about 7,314,717 (264)

Task-adaptive physical reservoir computing. [PDF]

Nat Mater, 2023
Reservoir computing is a neuromorphic architecture that may offer viable solutions to the growing energy costs of machine learning. In software-based machine learning, computing performance can be readily reconfigured to suit different computational ...
Lee O, Wei T, Stenning KD, Gartside JC, Prestwood D, Seki S, Aqeel A, Karube K, Kanazawa N, Taguchi Y, Back C, Tokura Y, Branford WR, Kurebayashi H.   +13 more
europepmc   +7 more sources

A Hopf physical reservoir computer [PDF]

Scientific Reports, 2021
Physical reservoir computing utilizes a physical system as a computational resource. This nontraditional computing technique can be computationally powerful, without the need of costly training.
Md Raf E Ul Shougat, XiaoFu Li, Tushar Mollik, Edmon Perkins   +3 more
doaj   +3 more sources

Physical Reservoir Computing

Vacuum and Surface Science
Reservoir Computing (RC) is an emerging field at the border of Computer Science and Physics. It leverages properties of dynamical systems with specific characteristics, called reservoirs, to provide additional computational power for analyzing data.
Banfield, Brendan
core   +4 more sources

Video recognition by physical reservoir computing in magnetic materials [PDF]

New Physics: Sae Mulli, 2023
Nonlinear spin dynamics in magnetic materials offers a promising avenue for implementing physical reservoir computing, one of the most accomplished brain-inspired frameworks for information processing.
Motome, Yukitoshi, Kobayashi, Kaito
core   +3 more sources

Physical reservoir computing with dynamical electronics [PDF]

, 2022
Since the advent of data-driven society, mass information generated from human activity and the natural environment has been collected, stored, processed, and then dispersed under conventional von Neumann architecture.
Liang, Xiangpeng
core   +3 more sources

Towards mixed physical node reservoir computing: light-emitting synaptic reservoir system with dual photoelectric output

Light: Science & Applications
Memristor-based physical reservoir computing holds significant potential for efficiently processing complex spatiotemporal data, which is crucial for advancing artificial intelligence.
Minrui Lian, Changsong Gao, Zhenyuan Lin, Liuting Shan, Cong Chen, Yi Zou, Enping Cheng, Changfei Liu, Tailiang Guo, Wei Chen, Huipeng Chen   +10 more
doaj   +2 more sources

Physical reservoir computing for biomedical applications

Neuromorphic Computing and Engineering
Reservoir computing (RC) is a feedforward computational framework derived from recurrent neural networks that leverages the high-dimensional dynamic behaviors of complex systems for efficient information processing.
Yuqi Ding, Bhavani Prasad Yalagala, Haobo Li, Mohammed Waqas Mughal, Hadi Heidari   +4 more
doaj   +3 more sources

RCbench: a unified framework for benchmarking reservoir computing systems

Neuromorphic Computing and Engineering
Reservoir computing (RC) is a computational framework where a fixed dynamical reservoir projects an input into a higher-dimensional state that is then analyzed by a readout , which is trained to map the reservoir state into the desired output.
Davide Pilati, Andrea Ceni, Fabio Michieletti, Claudio Gallicchio, Carlo Ricciardi, Gianluca Milano   +5 more
doaj   +2 more sources

Implementation of reservoir computing using coupled microelectromechanical drum resonators via sideband-pumped phonon–cavity dynamics [PDF]

Microsystems & Nanoengineering
Reservoir computing is a bio-inspired machine learning paradigm that exploits the intrinsic dynamics of nonlinear systems with fading memory for efficient temporal information processing.
Theresa Farah, Loïc Flis, Pierre Laly, Guo-En Chang, Jun-Yu Ou, Yoshishige Tsuchiya, Yan Pennec, Bahram Djafari-Rouhani, Xin Zhou   +8 more
doaj   +2 more sources

All-Optically Controlled Memristive Reservoir Computing Capable of Bipolar and Parallel Coding [PDF]

Nature Communications
Physical reservoir computing (RC) utilizes intrinsic dynamics of physical systems for efficient data processing. Emerging optoelectronic RC platforms merge the benefits of electronic and photonic computation. However, conventional designs are constrained
Lingxiang Hu, Dian Jiao, Kexuan Wang, Peihong Cheng, Jingrui Wang, Hamzah Al-madani, Li Zhang, Athanasios V. Vasilakos, Yang Chai, Zhizhen Ye, Fei Zhuge   +10 more
doaj   +2 more sources