arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.12249stat.MLcs.LG
收藏

复值神经网络综述

A Survey of Complex-Valued Neural Networks

Prairie View A&M University(普雷里维尤农工大学);Texas A&M University System(得克萨斯农工大学系统)

Joshua Bassey, Lijun Qian, Xianfang Li

摘要:

基于人工神经网络(ANN)的机器学习模型,特别是深度学习模型,已经广泛应用于计算机视觉、信号处理、无线通信和许多其他领域,其中复数自然地或通过设计出现。然而,目前大多数ANN和机器学习框架的实现都使用实数而不是复数。人们越来越感兴趣的是使用复数构建ANN,并探索所谓的复值神经网络(CVNN)相对于实值神经网络的潜在优势。在本文中,我们讨论了最近的发展,通过执行一个调查的工作,在文献中的CVNNs。具体而言,各种CVNN的激活函数,学习和优化,输入和输出表示,以及它们在任务中的应用,如信号处理和计算机视觉方面的详细审查提供,随后讨论了一些相关的挑战和未来的研究方向。

英文摘要:

Artificial neural networks (ANNs) based machine learning models and especially deep learning models have been widely applied in computer vision, signal processing, wireless communications, and many other domains, where complex numbers occur either naturally or by design. However, most of the current implementations of ANNs and machine learning frameworks are using real numbers rather than complex numbers. There are growing interests in building ANNs using complex numbers, and exploring the potential advantages of the so-called complex-valued neural networks (CVNNs) over their real-valued counterparts. In this paper, we discuss the recent development of CVNNs by performing a survey of the works on CVNNs in the literature. Specifically, a detailed review of various CVNNs in terms of activation function, learning and optimization, input and output representations, and their applications in tasks such as signal processing and computer vision are provided, followed by a discussion on some pertinent challenges and future research directions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑