Results 41 to 50 of about 16,073 (260)
Advanced Science, EarlyView.Task‐adaptive programmable optics enables label‐free virtual staining through optical‐attention‐guided acquisition and reconstruction. By optimizing wavelength, illumination angle, exposure time, and imaging depth, the framework learns task‐relevant optical measurements, generating clinically interpretable virtual stains with improved fidelity, non ...
Tianyue He +13 more
wiley +1 more source
Neural network training acceleration using NVIDIA CUDA technology for image recognition
Vestnik Samarskogo Gosudarstvennogo Tehničeskogo Universiteta. Seriâ: Fiziko-Matematičeskie Nauki, 2012 In this paper, an implementation of neural network trained by algorithm based on Levenberg-Marquardt method is presented. Training of neural network increased by almost 9 times using NVIDIA CUDA technology.
Alexander A Fertsev
doaj
Cybernetics and Information Technologies, 2013 The GPGPU (General Purpose Graphics Processing Units) have become a whole new area for research due to the fast development of GPU hardware and programming tools, such as CUDA (Compute Unified Device Architecture).
Yimu Ji +5 more
doaj +1 more source
Advanced Science, EarlyView.This study develops a multi‐dimensional vision Transformer‐based model, GAVR, to accurately distinguish gastric cancer T4a/b stages preoperatively. Validated across multi‐center cohorts, it achieves excellent performance and significantly improves radiologists’ diagnostic accuracy, offering a promising tool for clinical decision‐making.
Guoliang Zheng +20 more
wiley +1 more source
Analysis and development tools for efficient programs on parallel architectures
Труды Института системного программирования РАН, 2018 The article proposes methods for supporting development of efficient programs for modern parallel architectures, including hybrid systems. Specialized profiling methods designed for programmers tasked with parallelizing existing code are proposed.
Alexander Monakov +3 more
doaj +1 more source
, 2018 Abstract We add CUDA GPU C program code to RNAfold to enable both it to be run on nVidia gaming graphics hardware and so that many thousands of RNA secondary structures can be computed in parallel. RNAfold predicts the folding pattern for RNA molecules by using O( n 3
Langdon, W. B., Lorenz, Ronny
openaire +1 more source
Advanced Science, EarlyView.Using grilled lamb skewers as a model system, this work builds a multiscale coupling framework from oral processing to retronasal aroma perception, reveals dual‐kinetic release patterns and Electroencephalogram‐characterized central encoding features, and proposes an interpretable physics‐guided deep learning model validated by multiphysics simulation,
Che Shen +12 more
wiley +1 more source
Аlgorithm of fast computation of local image histograms on video card1
Informatika, 2019 An algorithm of parallel computation of image histograms of different types, including brightness and oriented gradient ones, on video cards of various types is presented.
Ph. S. Trotski, B. A. Zalesky
doaj
{CUDA}: Set constraints on GPUs
, 2021 Summary: Set constraints have been introduced in declarative programming languages in the Nineties as a consequence of a broader research on programming with sets and on computable set theory. General Purpose Graphics Processing Units (GPUs), originally developed for graphical purposes (e.g., for high definition video games), emerged recently as a ...
DOVIER AGOSTINO +3 more
openaire +4 more sources
CUDA Tutorial -- Cryptanalysis of Classical Ciphers Using Modern GPUs and CUDA
CoRR, 2021 CUDA (formerly an abbreviation of Compute Unified Device Architecture) is a parallel computing platform and API model created by Nvidia allowing software developers to use a CUDA-enabled graphics processing unit (GPU) for general purpose processing. This 90-pages tutorial introduces the CUDA concepts in an easy-to-grasp and interactive way with ready ...
Miroslav Dimitrov, Bernhard Esslinger
openaire +2 more sources