Results 191 to 200 of about 99,773 (316)

Connectivity Structure and Dynamics of Nonlinear Recurrent Neural Networks. [PDF]

Phys Rev X
Clark DG, Marschall O, van Meegen A, Litwin-Kumar A.   +3 more
europepmc   +1 more source

Integrated Field‐Free SOT Domain‐Wall Synapses and MTJ Stochastic Neurons for Hardware Boltzmann Machines

Advanced Functional Materials, EarlyView.
Field‐free spin‐orbit torque domain‐wall synapses integrated with stochastic MTJ neurons enable compact hardware Boltzmann machines. Leveraging intrinsic stochasticity and multi‐level conductance, the system achieves efficient probabilistic learning with high accuracy, demonstrating a scalable spintronic platform for energy‐efficient edge AI.
Aijaz H. Lone, Meng Tang, Camelia Florica, Bin He, Jingkai Xu, Selma Amara, Georgian Melinte, Xixiang Zhang, Gianluca Setti   +8 more
wiley   +1 more source

Adjoint propagation of error signal through modular recurrent neural networks for biologically plausible learning. [PDF]

Elife
Liu Z, Shu H, Wang L, Meng X, Wang Y, Li X, Wang W, Chen T.   +7 more
europepmc   +1 more source

Quantifying Subsurface Weak in‐Plane Magnetization of Mixed Phase BiFeO3 by Scanning Nitrogen Vacancy Magnetometry

Advanced Functional Materials, EarlyView.
We use scanning nitrogen vacancy magnetometry to directly image the weak in‐plane magnetic moments in mixed phase BiFeO3 at the nanoscale and quantify the local magnetic moments to be 18.8±2.0 μB/nm2 in the rhombohedral‐like phase and 1.5±0.6 μB/nm2 in the well‐known non‐magnetic tetragonal‐like phase.
Lei Wang, Zhewen Xu, Yuwen Xu, Björn Josteinsson, Simon Josephy, Dawei Zhang, Yunlong Sun, Heung‐Sik Park, Jihun Kim, Kanghyun Chu, Kyung Song, Danyang Wang, Chan‐Ho Yang, Andrea Morales, Jan Seidel   +14 more
wiley   +1 more source

Recurrent Neural Networks for Mexican Sign Language Interpretation in Healthcare Services. [PDF]

Sensors (Basel)
Becerril-Carrillo AJ, Selley-Rojas HJ, Guevara-Martínez E.   +2 more
europepmc   +1 more source

Feedback control guides credit assignment in recurrent neural networks

How do brain circuits learn to generate behaviour? While significant strides have been made in understanding learning in artificial neural networks, applying this knowledge to biological networks remains challenging.
Feulner, B, Gallego, JA, Kaleb, K, Clopath, C   +3 more
core  

Multimodal Perception and Machine Learning‐Empowered Human Machine Interfaces With Double‐Network Hydrogel Fibers

Advanced Functional Materials, EarlyView.
This work develops polyacrylamide‐alginate (PAM‐Alg) double‐network hydrogel fibers for multimodal perception and intelligent human‐machine interfaces. The covalent‐ionic network provides high strength, toughness, and stable conductivity. Easily woven into wearables and integrated with soft robots, the fibers enable object and temperature recognitions ...
Yujue Yang, Minyu Qiu, Di Tan, Xinlong Liu, Junze Zhang, Ziyu He, Jing Han, Yuanyuan Gao, Zihua Li, Hong Fu, Bingang Xu   +10 more
wiley   +1 more source

On the control of recurrent neural networks using constant inputs. [PDF]

IEEE Trans Automat Contr
Tamekue C, Chen R, Ching S.
europepmc   +1 more source

Electro‐Steric Ion Confinement in Polyelectrolyte Networks for Robust Nonvolatile Artificial Synapse

Advanced Functional Materials, EarlyView.
Polyelectrolyte stoichiometry governs ion transport and retention in electrolyte‐gated synaptic transistors. A PSS‐rich network creates electro‐steric ion confinement that suppresses ion back‐diffusion and stabilizes channel doping, enabling robust nonvolatile synaptic memory, linear weight updates, and low‐energy operation.
Donghwa Lee, Jinbo Kim, Myeongjin An, Jisoo Park, Junho Sung, Eunsung Hwang, Suhwan Seok, Seong‐Min Bak, Jeonghun Kim, Eunho Lee   +9 more
wiley   +1 more source

Competition and cooperation of assembly sequences in recurrent neural networks. [PDF]

PLoS Comput Biol
Stöber TM, Lehr AB, Nikzad A, Ganjtabesh M, Fyhn M, Kumar A.   +5 more
europepmc   +1 more source