当前位置: X-MOL 学术J. Big Data › 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.)
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
Journal of Big Data ( IF 8.1 ) Pub Date : 2021-03-31 , DOI: 10.1186/s40537-021-00444-8
Laith Alzubaidi 1, 2 , Jinglan Zhang 1 , Amjad J Humaidi 3 , Ayad Al-Dujaili 4 , Ye Duan 5 , Omran Al-Shamma 2 , J Santamaría 6 , Mohammed A Fadhel 7 , Muthana Al-Amidie 5 , Laith Farhan 8
Affiliation  

In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or even beating those provided by human performance. One of the benefits of DL is the ability to learn massive amounts of data. The DL field has grown fast in the last few years and it has been extensively used to successfully address a wide range of traditional applications. More importantly, DL has outperformed well-known ML techniques in many domains, e.g., cybersecurity, natural language processing, bioinformatics, robotics and control, and medical information processing, among many others. Despite it has been contributed several works reviewing the State-of-the-Art on DL, all of them only tackled one aspect of the DL, which leads to an overall lack of knowledge about it. Therefore, in this contribution, we propose using a more holistic approach in order to provide a more suitable starting point from which to develop a full understanding of DL. Specifically, this review attempts to provide a more comprehensive survey of the most important aspects of DL and including those enhancements recently added to the field. In particular, this paper outlines the importance of DL, presents the types of DL techniques and networks. It then presents convolutional neural networks (CNNs) which the most utilized DL network type and describes the development of CNNs architectures together with their main features, e.g., starting with the AlexNet network and closing with the High-Resolution network (HR.Net). Finally, we further present the challenges and suggested solutions to help researchers understand the existing research gaps. It is followed by a list of the major DL applications. Computational tools including FPGA, GPU, and CPU are summarized along with a description of their influence on DL. The paper ends with the evolution matrix, benchmark datasets, and summary and conclusion.



中文翻译:

深度学习回顾:概念、CNN 架构、挑战、应用、未来方向

在过去几年中,深度学习 (DL) 计算范式已被视为机器学习 (ML) 社区的黄金标准。此外,它已逐渐成为机器学习领域中使用最广泛的计算方法,从而在多个复杂的认知任务上取得了出色的结果,匹配甚至超越了人类的表现。深度学习的好处之一是能够学习大量数据。深度学习领域在过去几年中发展迅速,并已被广泛用于成功解决各种传统应用。更重要的是,深度学习在许多领域都超越了众所周知的机器学习技术,例如网络安全、自然语言处理、生物信息学、机器人和控制以及医疗信息处理等。尽管已经贡献了几篇回顾深度学习最新技术的著作,但所有这些都只解决了深度学习的一个方面,这导致了人们对它的整体缺乏了解。因此,在这篇文章中,我们建议使用更全面的方法,以便提供一个更合适的起点来全面理解深度学习。具体来说,本次审查试图对深度学习最重要的方面进行更全面的调查,包括最近添加到该领域的那些增强功能。本文特别概述了深度学习的重要性,介绍了深度学习技术和网络的类型。然后介绍了最常用的深度学习网络类型——卷积神经网络 (CNN),并描述了 CNN 架构的发展及其主要特征,例如,从 AlexNet 网络开始,到高分辨率网络 (HR.Net) 结束。最后,我们进一步提出挑战和建议的解决方案,以帮助研究人员了解现有的研究差距。接下来是主要深度学习应用程序的列表。总结了 FPGA、GPU 和 CPU 等计算工具,并描述了它们对深度学习的影响。本文最后给出了演化矩阵、基准数据集以及总结和结论。

更新日期:2021-03-31
down
wechat
bug