Overfitting and Underfitting Analysis for Deep Learning Based End-to-end Communication Systems

• Published in: International Conference on Wireless Communications and Signal Processing pp. 1 - 6
• Main Authors: Zhang, Haotian, Zhang, Lin, Jiang, Yuan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2019
• Subjects: Artificial neural networks; Communication systems; Deep learning; end-to-end transmission; energy-to-noise ratio; Machine learning; Modulation; neural network training; Receivers; Reliability; Training

In this paper, we study the deep learning (DL) based end- to-end transmission systems, then we present the analysis for the underfitting and overfitting phenomena which happen during the training of the neural networks (NNs). Different from the DL based image processing, the transmission systems req...