Results 111 to 120 of about 86,091 (310)
Advanced Science, EarlyView.We present an organic–inorganic heterostructure transistor array for neuromorphic computing, achieving 95.6% MNIST accuracy and 1.2 fJ per operation, with dynamic spatiotemporal encoding and precise vehicle direction detection under combined optical and electrical stimulation.
Wen‐Min Zhong +13 more
wiley +1 more source
, 2016 Ted Turner launched Cable News Network (CNN), the world’s first twenty-four-hour news channel, in 1980. Broadcast network journalists and media pundits initially dismissed CNN as the “Chicken Noodle Network,” pointing to its poor production values and small audience share.
openaire +1 more source
Efficient CNNs via Passive Filter Pruning
, 2023 Convolutional neural networks (CNNs) have shown state-of-the-art performance in various applications. However, CNNs are resource-hungry due to their requirement of high computational complexity and memory storage.
Plumbley, Mark D., Singh, Arshdeep
core
Advanced Science, EarlyView.This study achieves the synergistic integration of self‐powered sensing and edge AI acceleration to establish a real‐time fault diagnosis system. The proposed TENG‐based self‐powered bearing sensor (NSE‐TBS) and FPGA‐accelerated edge AI framework fundamentally break through the inherent limitations of conventional monitoring systems, including complex ...
Kehui Zhu +7 more
wiley +1 more source
Transform Domain Learning for Image Recognition
IEEE AccessImage and video classification are distinct tasks in computer vision. Three-dimensional convolutional neural networks (3D CNNs) are commonly employed for video classification, while two-dimensional convolutional neural networks (2D CNNs) are more ...
Dengtai Tan, Jinlong Zhao, Shichao Li
doaj +1 more source
Ultra‐Wide‐Field Noninvasive Imaging Through Scattering Media Via Physics‐Guided Deep Learning
Advanced Science, EarlyView.We propose a physics‐guided adaptive dual‐domain learning method for ultra‐wide‐field noninvasive imaging through scattering media, namely UNI‐Net. Our method not only reduces the requirement for real experimental data by an order of magnitude but also enables clear imaging of complex scenes with an ultra‐large field of view, which is 164 times the OME
Lintao Peng +5 more
wiley +1 more source
Nature CommunicationsWhenever a visual scene is cast onto the retina, much of it will appear degraded due to poor resolution in the periphery; moreover, optical defocus can cause blur in central vision.
Hojin Jang, Frank Tong
doaj +1 more source
Advanced Science, EarlyView.TarPass provides a rigorous benchmark for target‐aware de novo molecular generation by jointly evaluating protein‐ligand interactions, molecular plausibility, and drug‐likeness on 18 well‐studied targets. Results show that current models often fail to consistently surpass random baseline in target‐specific enrichment, while post hoc multi‐tier virtual ...
Rui Qin +11 more
wiley +1 more source
Triple‐Mode Ferroelectric Thin‐Film Transistor for Hybrid Electrical–Optical Reservoir Computing
Advanced Science, EarlyView.A triple‐mode ferroelectric thin‐film transistor is developed by integrating Si3N4/HZO/IGZO layers to realize three independent memory modes: electric long‐term, electric short‐term, and optical short‐term. This single‐device architecture functions as both a reservoir and readout layer, achieving 92.43% MNIST accuracy. It offers a fully hardware‐based,
Hyeonho Lee +9 more
wiley +1 more source
Partial Large Kernel CNNs for Efficient Super-Resolution
IEEE AccessRecently, in the image super-resolution (SR) domain, Transformers have outperformed Convolution Neural Networks (CNNs) with reduced computational complexity and parameters by modeling long-range dependencies input-dependently.
Dongheon Lee, Seokju Yun, Youngmin Ro
doaj +1 more source