Results 71 to 80 of about 27,097 (268)

A Reconfigurable Memristive Spiking Neuron Enabling Advanced Neuromorphic Computing

Advanced Science, EarlyView.
Pek Jun Tiw and co‐workers develop a reconfigurable memristive neuron that can exhibit four spiking behaviors with freely tunable spike train parameters. The neuron supports multiplexed spike encoding of multiple pieces of information. It also supports advanced neural network strategies, such as neural heterogeneity and dynamic mode switching ...
Pek Jun Tiw, Yuqi Li, Zhongyuan Li, Qihang Ding, Yuzhe Wang, Jiarong Wang, Yuchao Yang   +6 more
wiley   +1 more source

Study on lightning risk assessment and early warning for UHV DC transmission channel

High Voltage, 2019
Operation data show lightning faults account for >70% for the main ultra-high voltage (UHV) DC transmission channels, very different from the design view.
Shanqiang Gu, Jian Wang, Jian Wang, Min Wu, Juntian Guo, Chun Zhao, Jian Li   +6 more
doaj   +1 more source

A Physical Adaptive Material Motor Unit Neural Network: A Hygromorph Composite Material Machine

Advanced Science, EarlyView.
This study introduces a new class of material‐based intelligent machines. It presents a Physical Adaptive Material Motor Unit Neural Network, an assembly of smart 4D printed actuators and a controlling system that adapt through environmental interaction its shading behavior.
Charles de Kergariou, Helmut Hauser, David Correa   +2 more
wiley   +1 more source

Tensile Strength Prediction of Empty Palm Oil Bunch Fiber Composite with Artificial Neural Network

JEMMME (Journal of Energy, Mechanical, Material, and Manufacturing Engineering)
As the leading global producer of palm oil, Indonesia encounters substantial environmental challenges arising from the waste generated by empty palm oil fruit bunches (EPOFB).
Hery Tri Waloyo, Agus Mujianto, Richie Feriyanto   +2 more
doaj   +1 more source

Backpropagation and Biological Plausibility

CoRR, 2018
By and large, Backpropagation (BP) is regarded as one of the most important neural computation algorithms at the basis of the progress in machine learning, including the recent advances in deep learning. However, its computational structure has been the source of many debates on its arguable biological plausibility. In this paper, it is shown that when
Alessandro Betti, Marco Gori, Giuseppe Marra   +2 more
openaire   +2 more sources

Adaptive Conductive Systems: Enabling Deformable Electronics Through Engineered Materials, Circuits, and Intelligent Systems

Advanced Science, EarlyView.
This review presents the research advances of adaptive conductive systems from the perspective of materials, circuits, systems, and applications. Deformable conductors consist of substrates/matrices and conductive materials, structural design of circuit interconnections, fabrication of circuit interconnections, as well as intelligent systems ...
Yufei Lu, Siyu Liang, Jingyi Niu, Jie Chen, Shuo Zhang, Hongjian Zhang, Dongsheng Jia, Wei Huang   +7 more
wiley   +1 more source

Desain Sistem Pendeteksi untuk Citra Base Sub-assembly dengan Algoritma Backpropagation

Jurnal Rekayasa Elektrika, 2017
Object identification technique using machine vision has been implemented in industrial of electronic manufacturers for years. This technique is commonly used for reject detection (for disqualified product based on existing standard) or defect detection.
Kasdianto Kasdianto, Siti Aisyah
doaj   +1 more source

MethyAnno: An Interpretable Automated Annotation Method Leveraging Multi‐Scale Information and Metric Learning Framework for scDNAm Data

Advanced Science, EarlyView.
MethyAnno enables robust and interpretable annotation of single‐cell DNA methylation data by integrating multi‐scale epigenetic information, bidirectional cross‐attention, and prototype‐based metric learning. The framework resolves rare and novel cell types across datasets while revealing cell‐type‐specific epigenetic signatures associated with disease
Yuhang Jia, Siyu Li, Songming Tang, Keju Gu, Shengquan Chen   +4 more
wiley   +1 more source

LLMs as Representation Generators for Gradient‐Free Scientific Optimization: A Case Study in Battery Fast Charging

Advanced Science, EarlyView.
Large language models serve as representation generators for gradient‐free scientific optimization. Two complementary approaches produce executable battery‐charging policies either directly or through LLM‐designed neural representations coupled to Bayesian optimization.
Ge Lei, Ferran Brosa Planella, Sterling G. Baird, Samuel J. Cooper   +3 more
wiley   +1 more source

Hardware Acceleration of Stochastic Neural Networks Enabled by Bit‐Cell Level Co‐Design of Magnetic Tunnel Junctions

Advanced Science, EarlyView.
An MTJ‐based probabilistic processing‐in‐memory architecture unites nonvolatile storage, local entropy generation, and stochastic computation within each memory cell. Stored multi‐bit weights are converted directly into programmable stochastic bitstreams, enabling neural‐network inference, adaptive Ising optimization, and uncertainty‐aware Bayesian ...
Qiuyuan Wang, Dooyong Koh, Brooke McGoldrick, Tudor Mocioi, Yabin Fan, Marc Baldo, Luqiao Liu   +6 more
wiley   +1 more source