Neural network training acceleration using NVIDIA CUDA technology for image recognition

DOI10.14498/VSGTU990MaRDI QIDQ4960048zbMATH OpenOpenAlexFDO

Authors Aleksandr Aleksandrovich Fertsev

Publication date 8 April 2020

Published in Vestnik Samarskogo Gosudarstvennogo Tekhnicheskogo Universiteta. Seriya Fiziko-Matematicheskie Nauki (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL http://mathnet.ru/eng/vsgtu990

zbMATH Keywords

CUDAgraphics processing unitimage recognitionLevenberg-Marquardt methodneural networks

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Neural nets and related approaches to inference from stochastic processes (62M45) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Recommendations

• GPU implementation of neural networks
• Implementation of the fast algorithm for geometrical coding of digital images with the use of CUDA architecture
• An implementation of scatter search to train neural networks for brain lesion recognition
• Parallelization of cellular neural networks on GPU
• Human Face Recognition Using Accelerated Multilayer Perceptrons

Cites work

• An Algorithm for Least-Squares Estimation of Nonlinear Parameters

Cited in

(5)

• GPU implementation of neural networks
• A search engine based on neural correlation matrix memories
• Optimization of neural network training for image recognition based on trigonometric polynomial approximation
• Scene recognition based on a partially connected neural network
• An implementation of scatter search to train neural networks for brain lesion recognition

Describes a project that uses

Uses Software

• CUDA

This page was built for publication: Neural network training acceleration using NVIDIA CUDA technology for image recognition

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4960048)