AUTHOR=Wang Danshi , Zhang Min 

TITLE=Artificial Intelligence in Optical Communications: From Machine Learning to Deep Learning

JOURNAL=Frontiers in Communications and Networks

VOLUME=Volume 2 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/communications-and-networks/articles/10.3389/frcmn.2021.656786

DOI=10.3389/frcmn.2021.656786

ISSN=2673-530X

ABSTRACT=Techniques from artificial intelligence have been widely applied in optical communication and network evolving from the early machine learning (ML) to the recent deep learning (DL). This paper focuses on the state-of-the-art DL algorithms and aims at highlighting the contributions of DL to optical communications. Considering the characteristics of different DL algorithms and data types, we review multiple DL-enabled solutions to optical communication. First, convolutional neural network (CNN) is used for image recognition and recurrent neural network (RNN) is applied for sequential data analysis. A variety of functions can be achieved by the corresponding DL algorithms through processing the different image data and sequential data collected from optical communication. A data-driven channel modeling method is also proposed to replace the conventional block-based modeling method and improve the end-to-end learning performance. Additionally, generative adversarial network (GAN) is introduced for data augmentation to expand the training dataset from the rare experimental data. Finally, deep reinforcement learning (DRL) is applied to perform self-configuration and adaptive allocation for optical network.