Artificial intelligence and wireless communications
- PDF / 2,134,787 Bytes
- 13 Pages / 595.276 x 841.89 pts (A4) Page_size
- 44 Downloads / 264 Views
1
Frontiers of Information Technology & Electronic Engineering www.jzus.zju.edu.cn; engineering.cae.cn; www.springerlink.com ISSN 2095-9184 (print); ISSN 2095-9230 (online) E-mail: [email protected]
Perspective:
Artificial intelligence and wireless communications Jun WANG1 , Rong LI‡1 , Jian WANG1 , Yi-qun GE2 , Qi-fan ZHANG2 , Wu-xian SHI2 1Wireless 2Wireless
Technology Laboratory, Huawei Technologies Co., Ltd., Hangzhou 310051, China Technology Laboratory, Huawei Technologies Co., Ltd., Ottawa K0A3M0, Canada
E-mail: {justin.wangjun, lirongone.li, wangjian23, yiqun.ge, qifan.zhang, wuxian.shi}@huawei.com Received Sept. 27, 2019; Revision accepted Mar. 27, 2020; Crosschecked May 18, 2020
Abstract: The applications of artificial intelligence (AI) and machine learning (ML) technologies in wireless communications have drawn significant attention recently. AI has demonstrated real success in speech understanding, image identification, and natural language processing domains, thus exhibiting its great potential in solving problems that cannot be easily modeled. AI techniques have become an enabler in wireless communications to fulfill the increasing and diverse requirements across a large range of application scenarios. In this paper, we elaborate on several typical wireless scenarios, such as channel modeling, channel decoding and signal detection, and channel coding design, in which AI plays an important role in wireless communications. Then, AI and information theory are discussed from the viewpoint of the information bottleneck. Finally, we discuss some ideas about how AI techniques can be deeply integrated with wireless communication systems. Key words: Wireless communications; Artificial intelligence; Machine learning https://doi.org/10.1631/FITEE.1900527 CLC number: TN92
1 Introduction Due to the development of advanced computing capabilities, progress in algorithms, and accessibility to big data, artificial intelligence (AI) is ushering in a new wave of technical revolution in human society (Russell and Norvig, 2002). Machine learning (ML), comprising a more specific subset of AI technologies, helps computers process and learn from data on their own. To date, machines aided by ML technologies have already been performing comparably or even better compared with human beings in many fields, such as voice and image recognition, game playing, semantic analysis, and drug discovery. Most of the aforementioned success has been brought about by the introduction of neural networks (NNs) inspired by the structure of the human brain. In ‡
Corresponding author
ORCID: Jun WANG, https://orcid.org/0000-0002-8127-9124; Rong LI, https://orcid.org/0000-0003-1040-1484 c Zhejiang University and Springer-Verlag GmbH Germany, part of Springer Nature 2020
the learning process, neurons are combined into certain structures to form a network, i.e., a training model; experience (data) is fed into the network to help determine the weight values between neurons. A target (either more reward or less penalty) is set up to facilitate th
Data Loading...
