Results 41 to 50 of about 1,932,721 (285)

Optimizations of reservoir computing in a nonlinear nanomechanical resonator

, 2023
National audienceReservoir computing is a branch of artificial intelligence derived from recurrent neuron network theory. It has the advantage of being efficient in many applications like speech recognition, image classification and time series ...
Rabenimanana, Toky Harrison, Zhou, Xin
core   +3 more sources

Time series reconstructing using calibrated reservoir computing

Scientific Reports, 2022
Reservoir computing, a new method of machine learning, has recently been used to predict the state evolution of various chaotic dynamic systems. It has significant advantages in terms of training cost and adjusted parameters; however, the prediction ...
Yeyuge Chen, Yu Qian, Xiaohua Cui
doaj   +1 more source

Recent Advances in Reservoir Computing With A Focus on Electronic Reservoirs

, 2020
Reservoir Computing is a subset of recurrent neural networks which can compute temporal-spatial tasks efficiently. In reservoir computing inputs are randomly connected to fixed untrained nodes in the reservoir layer.
Yang Yi, Zhang, Yuhao, Nowshin, Fabiha, Yuhao Zhang, Liu, Lingjia, Lingjia Liu, Yi, Yang, Fabiha Nowshin   +7 more
core   +1 more source

Reservoir Computing Architectures for Modeling Robot Navigation Systems [PDF]

, 2011
This thesis proposes a new efficient and biologically inspired way of modeling navigation tasks for autonomous mobile robots having restrictions on cost, energy consumption, and computational complexity (such as household and assistant robots).
ANTONELO, Eric Aislan
core   +2 more sources

Differentiable reservoir computing

CoRR, 2019
60 ...
Lyudmila Grigoryeva, Ortega Lahuerta, Juan-Pablo   +1 more
openaire   +6 more sources

Reservoir computing with solitons

New Journal of Physics, 2021
Reservoir computing is a promising framework that facilitates the approach to physical neuromorphic hardware by enabling a given nonlinear physical system to act as a computing platform.
Nuno Azevedo Silva, Tiago D Ferreira, Ariel Guerreiro   +2 more
doaj   +1 more source

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   +1 more source

Rotating neurons for all-analog implementation of cyclic reservoir computing

Nature Communications, 2022
Reservoir computing has demonstrated high-level performance, however efficient hardware implementations demand an architecture with minimum system complexity. The authors propose a rotating neuron-based architecture for physically implementing all-analog
Xiangpeng Liang, Yanan Zhong, Jianshi Tang, Zhengwu Liu, Peng Yao, Keyang Sun, Qingtian Zhang, Bin Gao, Hadi Heidari, He Qian, Huaqiang Wu   +10 more
doaj   +1 more source

Learning navigation attractors for mobile robots with reinforcement learning and reservoir computing [PDF]

, 2011
peer reviewedAutonomous robot navigation in partially observable environments is a complex task because the state of the environment can not be completely determined only by the current sensory readings of a robot.
ANTONELO, Eric Aislan, Depeweg, Stefan, Schrauwen, Benjamin   +2 more
core   +1 more source

A high-performance deep reservoir computer experimentally demonstrated with ion-gating reservoirs

Communications Engineering
While physical reservoir computing is a promising way to achieve low power consumption neuromorphic computing, its computational performance is still insufficient at a practical level. One promising approach to improving its performance is deep reservoir
Daiki Nishioka, Takashi Tsuchiya, Masataka Imura, Yasuo Koide, Tohru Higuchi, Kazuya Terabe   +5 more
doaj   +1 more source