当前位置: X-MOL 学术IEEE Trans. Cognit. Commun. Netw. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Random Fourier Feature-Based Deep Learning for Wireless Communications
IEEE Transactions on Cognitive Communications and Networking ( IF 8.6 ) Pub Date : 2022-04-05 , DOI: 10.1109/tccn.2022.3164898
Rangeet Mitra 1 , Georges Kaddoum 1
Affiliation  

Deep-learning (DL) has emerged as a powerful machine-learning technique for several problems encountered in generic wireless communications. Also, random Fourier Features (RFF) based DL has emerged as an attractive solution for several machine-learning problems; yet existing works lack rigorous analytical results to justify the viability of RFF based DL. To address this gap, we analytically quantify the viability of RFF based DL in this paper. Precisely, we present analytical proofs which show that the RFF based DL architectures have lower approximation-error and a lower probability of misclassification as compared to classical DL architectures for a fixed dataset-size. In addition, a new distribution-dependent RFF (DDRFF) is proposed to facilitate DL architectures with low training-complexity. The presented analytical contributions and the DDRFF are validated by relevant case-studies such as: a) line of sight (LOS)/non-line of sight (NLOS) classification, and b) message-passing based detection of low-density parity check (LDPC) codes over nonlinear visible light communication (VLC) channels. Especially, in the low training-data regime, the presented simulations depict significant performance gains for RFF based DL. Lastly, in all the presented simulations, it is observed that the proposed DDRFFs significantly outperform RFFs, which make them useful for potential machine-learning/DL applications for communication systems.

中文翻译:

基于随机傅里叶特征的无线通信深度学习

深度学习 (DL) 已成为解决通用无线通信中遇到的几个问题的强大机器学习技术。此外,基于随机傅立叶特征 (RFF) 的 DL 已成为解决若干机器学习问题的有吸引力的解决方案;然而,现有的工作缺乏严格的分析结果来证明基于 RFF 的 DL 的可行性。为了解决这一差距,我们在本文中分析量化了基于 RFF 的 DL 的可行性。准确地说,我们提出的分析证明表明,与固定数据集大小的经典 DL 架构相比,基于 RFF 的 DL 架构具有更低的近似误差和更低的误分类概率。此外,提出了一种新的依赖于分布的 RFF (DDRFF),以促进具有低训练复杂度的 DL 架构。所提出的分析贡献和 DDRFF 通过相关案例研究得到验证,例如:a) 视线 (LOS)/非视线 (NLOS) 分类,以及 b) 基于消息传递的低密度奇偶校验检测(LDPC) 码在非线性可见光通信 (VLC) 信道上。特别是,在低训练数据情况下,所提出的模拟描绘了基于 RFF 的 DL 的显着性能提升。最后,在所有提出的模拟中,观察到提出的 DDRFF 显着优于 RFF,这使得它们对通信系统的潜在机器学习/DL 应用很有用。b) 基于消息传递的非线性可见光通信 (VLC) 信道上的低密度奇偶校验 (LDPC) 码检测。特别是,在低训练数据情况下,所提出的模拟描绘了基于 RFF 的 DL 的显着性能提升。最后,在所有提出的模拟中,观察到提出的 DDRFF 显着优于 RFF,这使得它们对通信系统的潜在机器学习/DL 应用很有用。b) 基于消息传递的非线性可见光通信 (VLC) 信道上的低密度奇偶校验 (LDPC) 码检测。特别是,在低训练数据情况下,所提出的模拟描绘了基于 RFF 的 DL 的显着性能提升。最后,在所有提出的模拟中,观察到提出的 DDRFF 显着优于 RFF,这使得它们对通信系统的潜在机器学习/DL 应用很有用。
更新日期:2022-04-05
down
wechat
bug