Results 141 to 150 of about 102,874 (306)
Polarization Engineering in Vinylene‐Linked COFs Toward Efficient Neuromorphic Computing
A vinyl‐linked covalent organic framework (COF‐DIBPY) was synthesized on a conductive substrate for memristor applications. Redox reactions and bromide migration enable low‐voltage (0.5V) conductance switching with high analog on/off ratio (15.7). The device was further integrated into a speech emotion recognition system for acoustic simulation and ...
Hao Wang +5 more
wiley +1 more source
FPGA Acceleration of CNNs Using OpenCL
: Convolutional Neural Network (CNN) has achieved state-of-the-art performance in numerous applications like computer vision, natural language processing, robotics etc.
core
Hierarchical Multi‐Mode Computing in Interlayer‐Coupled 3D RRAM Crossbar Arrays
2‐deck RRAM crossbar array provides a versatile hardware platform for multifunctional in‐memory computing. Stacked, series, and entropy node configurations enable multi‐layer conductance modulation, logic‐in‐memory operation, genetic learning, and reconfigurable physical unclonable functions.
Seungman Park +7 more
wiley +1 more source
PDE-CNNs: Axiomatic Derivations and Applications
PDE-based Group Convolutional Neural Networks (PDE-G-CNNs) use solvers of evolution PDEs as substitutes for the conventional components in G-CNNs. PDE-G-CNNs can offer several benefits simultaneously: fewer parameters, inherent equivariance, better ...
Smets, Bart M. N. +3 more
core
Bioinspired Ionochromic Neuromorphic Transistors for Robotic Intelligent Perception
A bioinspired ionochromic neuromorphic transistor couples synaptic conductance modulation with reversible color change through voltage‐controlled ion doping in P3HT/ion gel, mimicking biological synaptic plasticity, and chameleon‐like color regulation.
Quanxing Yao +10 more
wiley +1 more source
We developed UCtracker, a urine DNA methylation–based deep learning model, for noninvasive diagnosis and postoperative surveillance of urothelial carcinoma. UCtracker demonstrates high diagnostic accuracy, robustness at ultralow sequencing depth, early recurrence detection, and dynamic risk‐stratified monitoring of molecular residual disease ...
Shengwei Xiong +19 more
wiley +1 more source
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 +4 more
wiley +1 more source
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 +11 more
wiley +1 more source
Towards energy-efficient CNNs using structured pruning
Deep Convolutional Neural Networks (CNNs) have gained immense popularity over the past decade due to their exceptional performance, especially in imaging applications. However, the primary focus has been on improving model accuracy, often overlooking the
Diffa G. Pinto, Sunil B. Mane
doaj +1 more source
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 +10 more
wiley +1 more source

