A Frequency-Domain Convolutional Neural Network Architecture Based on the Frequency-Domain Randomized Offset Rectified Linear Unit and Frequency-Domain Chunk Max Pooling Method

A Frequency-Domain Convolutional Neural Network Architecture Based on the Frequency-Domain Randomized Offset Rectified Linear Unit and Frequency-Domain Chunk Max Pooling Method

It is of great importance to construct a convolutional neural network architecture in the frequency domain to explore the theory of deep learning in the frequency domain. However, due to the complexity of the construction mechanism of the forward and backward pipelines needed to train the convolutio...

Full description

Bibliographic Details
Main Authors: Jinhua Lin, Lin Ma, Jingxia Cui
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Convolutional neural network
deep learning
frequency domain
activation function
pooling method
Online Access:https://ieeexplore.ieee.org/document/9097887/

Internet

https://ieeexplore.ieee.org/document/9097887/

Similar Items