Optimization of neural network training for image recognition based on trigonometric polynomial approximation

DOI10.1134/S0361768821080272MaRDI QIDQ2064396zbMATH OpenOpenAlexFDO

Authors N. Vershkov, Andrei Tchernykh, B. Pulido-Gaytan, N. Kuchukova, Mikhail Babenko, Jorge M. Cortés-Mendoza, Viktor Kuchukov

Publication date 5 January 2022

Published in Programming and Computer Software (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1134/s0361768821080272

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Trigonometric approximation (42A10) Computing methodologies for image processing (68U10)

Recommendations

• scientific article; zbMATH DE number 992830
• Design and analysis of an efficient neural network model for solving nonlinear optimization problems
• Neural network training acceleration using NVIDIA CUDA technology for image recognition
• An outer-approximation guided optimization approach for constrained neural network inverse problems
• A neural network model structure study based on Fourier

Cites work

• scientific article; zbMATH DE number 3983811 (Why is no real title available?)
• scientific article; zbMATH DE number 3755177 (Why is no real title available?)
• scientific article; zbMATH DE number 3525015 (Why is no real title available?)
• scientific article; zbMATH DE number 1225807 (Why is no real title available?)
• scientific article; zbMATH DE number 1110192 (Why is no real title available?)
• scientific article; zbMATH DE number 1392848 (Why is no real title available?)
• scientific article; zbMATH DE number 3187230 (Why is no real title available?)
• A logical calculus of the ideas immanent in nervous activity
• Collected Works
• Digital signal processing. System analysis and design.
• Implementation of spectral transformations in the class of fast neural networks
• On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition
• Search for the global extremum using the correlation indicator for neural networks supervised learning
• Training Products of Experts by Minimizing Contrastive Divergence

Describes a project that uses

Uses Software

• ADADELTA
• PyTorch
• MNIST

This page was built for publication: Optimization of neural network training for image recognition based on trigonometric polynomial approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2064396)