Results 151 to 160 of about 3,605,315 (303)

Pattern‐Aware Intelligence Enables Nondestructive, Rapid Quantification of High‐Aspect‐Ratio Silicon Etching

Advanced Science, EarlyView.
Pattern‐dependent etching is converted into a physical prior for intelligent reconstruction of high‐aspect‐ratio silicon structures. Combining YOLO‐Pose feature extraction with a topography network, the framework retrieves depth, sidewall angle, and scallop texture from minimal destructive observations, enabling accurate cross‐scale metrology and near ...
Shuyan He, Lang Chen, Bo Wen, Yufeng Jin, Wei Wang   +4 more
wiley   +1 more source

Deep‐Learning‐Driven High‐Fidelity In Vivo Hyperspectral Fluorescence Imaging Under Extreme Photon‐Limited Conditions

Advanced Science, EarlyView.
Highly overlapping fluorescent signals become distinguishable in photon‐limited living organisms via advanced imaging with intelligent reconstruction. The resulting in vivo hyperspectral imaging capability reveals nanoplastic uptake and circulation in live zebrafish, providing a new approach for studying complex biological and environmental processes ...
Renjian Li, Shutao Wu, Kaixiang Li, Zhenyu An, Yuwen Ben, Guiye LI, Sunil Kumar, James Mcginty, Tawfique Hasan, Songnian Fu, Meng Zhang, LingLing Chen   +11 more
wiley   +1 more source

Enhanced image classification with a fast-learning shallow convolutional neural network

, 2015
We present a neural network architecture and training method designed to enable very rapid training and low implementation complexity. Due to its training speed and the absence of iteratively-tuned parameters, the method has strong potential for ...
Vladusich, T., Mark D. McDonnell, Tony Vladusich, McDonnell, M.   +3 more
core   +1 more source

Deciphering Anti‐Cancer Drug Efficacy Through Nanomechanical Vibrations in Living Gastric Cancer Organoids

Advanced Science, EarlyView.
This study developed an efficacy assessment platform that integrates patient‐derived gastric cancer organoids, atomic force microscopy (AFM)‐based nanomechanical vibration detection, deep learning analysis, and organoid mechanical modeling. It detects picomolar drug effects within 0.1 s signal, achieves 97% classification accuracy, and offers non ...
Ting Zhang, Qiubo Chen, Shihai Lan, Liang Zhu, Shuaiyu Liu, Yan Xia, Yalu Zhang, Hanhui Yao, Yongman Liu, Shangquan Wu, Qingchuan Zhang   +10 more
wiley   +1 more source

Interleaving cortex-analog mixing improves deep non-negative matrix factorization networks

Frontiers in Computational Neuroscience
Considering biological constraints in artificial neural networks has led to dramatic improvements in performance. Nevertheless, to date, the positivity of long-range signals in the cortex has not been shown to yield improvements.
Mahbod Nouri, David Rotermund, Alberto Garcia-Ortiz, Klaus R. Pawelzik   +3 more
doaj   +1 more source

Groundwater Rise Sustains the World's Largest Alpine Water System Under Global Warming

Advanced Science, EarlyView.
Shallow groundwater depth (SGWD) across the non‐permafrost plains of the Qinghai–Xizang Plateau decreased at averagely 0.02 m year−1, adding 31.44 Gt of freshwater storage from 2000 to 2020 and sustaining ∼53 500 km2 of alpine ecosystems. A vadose‐zone capacity of 426.6 Gt reveals these aquifers as promising reservoirs, highlighting groundwater's ...
Jianqing Du, Zhixiang Niu, Yanfen Wang, Shirui Zhou, Youqing Yang, Xiang Wei, Haishan Niu, Yitao Zhang, Anquan Xia, Yali Liu, Yanbin Hao, Kai Xue, Bingfang Wu, Xinquan Zhao, Tandong Yao, Yiyu Chen   +15 more
wiley   +1 more source

Food Image Recognition by Using Convolutional Neural Networks (CNNs)

CoRR, 2016
Food image recognition is one of the promising applications of visual object recognition in computer vision. In this study, a small-scale dataset consisting of 5822 images of ten categories and a five-layer CNN was constructed to recognize these images.
openaire   +2 more sources

Evolutionary Design of Convolutional Neural Networks

, 2021
The aim of this Master's thesis is to describe basic technics of evolutionary computing, convolutional neural networks (CNN), and automated design of neural networks using neuroevolution ( NAS - Neural Architecture Search ).
Pristaš, Ján
core  

Robust Stitching Interface and Deep Learning Empowered Hydrogel Human‐Machine Interface

Advanced Science, EarlyView.
A molecular design strategy is presented that exploits synergistic carboxylate anion–quaternary ammonium interactions to simultaneously strengthen the hydrogel–PET interface and the bulk hydrogel network. Integrated with deep learning signal processing, the stable hydrogel–PET interface enables consistent signal acquisition and reliable human‐machine ...
Hao Dong, Yiming Luo, Chuanliu Liu, Mahamood Modupe Rasheedat, Wenjiayi Tan, Fangyu Zhao, Yixue Zhang, Chris Connor, Hua Hou, Hamdy Khamees Thabet, Ben Bin Xu, Huige Wei   +11 more
wiley   +1 more source

Battery‐Inspired Electrochemical Synapses for Neuromorphic Applications

Advanced Science, EarlyView.
Battery‐ion‐inspired synaptic devices integrate diverse electrolyte systems (solid, ion‐gel, liquid) with transition metal oxides, two‐dimensional materials, and organic channels to regulate ion‐electron coupling. By tailoring ion transport and host interactions, these platforms enable controllable plasticity and energy‐efficient implementations for ...
Won Woo Lee, SeongCheol Jang, Wangmyung Choi, Jaewon Park, Jaehyun Hur, Hocheon Yoo, Hyun‐Suk Kim   +6 more
wiley   +1 more source