Results 31 to 40 of about 101,043 (267)
Spintronic reservoir computing without driving current or magnetic field
Recent studies have shown that nonlinear magnetization dynamics excited in nanostructured ferromagnets are applicable to brain-inspired computing such as physical reservoir computing.
Tomohiro Taniguchi +3 more
doaj +1 more source
Morphological properties of mass-spring networks for optimal locomotion learning [PDF]
Robots have proven very useful in automating industrial processes. Their rigid components and powerful actuators, however, render them unsafe or unfit to work in normal human environments such as schools or hospitals.
Carette, Benonie +4 more
core +2 more sources
Herein, physical reservoir computing with a redox‐based ion‐gating reservoir (redox‐IGR) comprising LixWO3 thin film and lithium‐ion conducting glass ceramic (LICGC) is demonstrated.
Tomoki Wada +5 more
doaj +1 more source
Computational Capacity and Energy Consumption of Complex Resistive Switch Networks [PDF]
Resistive switches are a class of emerging nanoelectronics devices that exhibit a wide variety of switching characteristics closely resembling behaviors of biological synapses.
Alireza Goudarzi +4 more
core +4 more sources
Connecting reservoir computing with statistical forecasting and deep neural networks
Standfirst Among the existing machine learning frameworks, reservoir computing demonstrates fast and low-cost training, and its suitability for implementation in various physical systems.
Lina Jaurigue, Kathy Lüdge
doaj +1 more source
The van der Pol physical reservoir computer
Abstract The van der Pol oscillator has historical and practical significance to spiking neural networks. It was proposed as one of the first models for heart oscillations, and it has been used as the building block for spiking neural networks.
Md Raf E Ul Shougat, Edmon Perkins
openaire +2 more sources
More than 3.5 billion people live in rural areas, where water and water energy resources play an important role in ensuring sustainable and productive rural economies.
Ivan S. Maksymov
doaj +1 more source
Modelling Reservoir Computing with the Discrete Nonlinear Schr\"odinger Equation
We formulate, using the discrete nonlinear Schroedinger equation (DNLS), a general approach to encode and process information based on reservoir computing. Reservoir computing is a promising avenue for realizing neuromorphic computing devices.
Boman, Magnus +2 more
core +1 more source
Video Recognition by Physical Reservoir Computing in Magnetic Materials
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. In this study, we investigate the practical utility of magnetic physical reservoirs by assessing their performance in a video recognition task ...
Kobayashi, Kaito, Motome, Yukitoshi
openaire +2 more sources
Reservoir Computing Approach to Robust Computation using Unreliable Nanoscale Networks
As we approach the physical limits of CMOS technology, advances in materials science and nanotechnology are making available a variety of unconventional computing substrates that can potentially replace top-down-designed silicon-based computing devices ...
A. Atiya +22 more
core +1 more source

