Related references
Note: Only part of the references are listed.
Article
Mathematics, Applied
Theory of the Frequency Principle for General Deep Neural Networks
Tao Luo et al.
Summary: This paper rigorously investigates the Frequency Principle in the training dynamics of Deep Neural Networks (DNNs) at three stages: initial, intermediate, and final. The results, presented in the form of theorems, are general and applicable to multilayer networks with general activation functions and a wide range of loss functions, providing a theoretical foundation for a better understanding of the training process of DNNs.
CSIAM TRANSACTIONS ON APPLIED MATHEMATICS (2021)
Proceedings Paper
Computer Science, Theory & Methods
Dilated Causal Convolutional Model For RF Fingerprinting
Josh Robinson et al.
2020 10TH ANNUAL COMPUTING AND COMMUNICATION WORKSHOP AND CONFERENCE (CCWC) (2020)
Article
Computer Science, Information Systems
Radar Signal Intra-Pulse Modulation Recognition Based on Convolutional Neural Network and Deep Q-Learning Network
Zhiyu Qu et al.
IEEE ACCESS (2020)