Paper
18 November 2024 A convolutional neural network training algorithm based on frequency domain transform
Zhichen Wang, Longliang Chen
Author Affiliations +
Proceedings Volume 13403, International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2024) ; 1340302 (2024) https://doi.org/10.1117/12.3051686
Event: International Conference on Algorithms, High Performance Computing, and Artificial Intelligence, 2024, Zhengzhou, China
Abstract
This article proposes a convolutional neural network training algorithm based on frequency domain transformation to address the issues of high computational complexity and complex training processes in convolutional neural networks. Through experimental verification, this algorithm can further improve the accuracy of neural networks compared to existing frequency domain transformation algorithms.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Zhichen Wang and Longliang Chen "A convolutional neural network training algorithm based on frequency domain transform", Proc. SPIE 13403, International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2024) , 1340302 (18 November 2024); https://doi.org/10.1117/12.3051686
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Education and training

Neural networks

Convolutional neural networks

Evolutionary algorithms

Convolution

Matrices

Object detection

Back to Top