Rethinking Motivation of Deep Neural Architectures

doi:10.1109/MCAS.2020.3027222

CSpace > 系统科学研究所

	Rethinking Motivation of Deep Neural Architectures
	Luo, Weilin 1; Lu, Jinhu 1,2,3,4,5,6; Li, Xuerong7 ; Chen, Lei 1,3,8; Liu, Kexin 1,9
	2020
发表期刊	IEEE CIRCUITS AND SYSTEMS MAGAZINE
ISSN	1531-636X
卷号	20 期号:4 页码:65-76
摘要	Nowadays, deep neural architectures have acquired great achievements in many domains, such as image processing and natural language processing. In this paper, we hope to provide new perspectives for the future exploration of novel artificial neural architectures via reviewing the proposal and development of existing architectures. We first roughly divide the influence domain of intrinsic motivations on some common deep neural architectures into three categories: information processing, information transmission and learning strategy. Furthermore, to illustrate how deep neural architectures are motivated and developed, motivation and architecture details of three deep neural networks, namely convolutional neural network (CNN), recurrent neural network (RNN) and generative adversarial network (GAN), are introduced respectively. Moreover, the evolution of these neural architectures are also elaborated in this paper. At last, this review is concluded and several promising research topics about deep neural architectures in the future are discussed.
DOI	10.1109/MCAS.2020.3027222
收录类别	SCI
语种	英语
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000612854700005
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/58089
专题	系统科学研究所
通讯作者	Lu, Jinhu
作者单位	1.Beihang Univ, Sch Automat Sci & Elect Engn, Beijing, Peoples R China 2.Chinese Acad Sci, AMSS, Beijing, Peoples R China 3.RMIT Univ, Melbourne, Vic, Australia 4.Princeton Univ, Princeton, NJ 08544 USA 5.Natl Key Res & Dev Program China, Beijing, Peoples R China 6.Innovat Res Grp NNSF China, Beijing, Peoples R China 7.Chinese Acad Sci, Acad Math & Syst Sci, Beijing, Peoples R China 8.Okayama Prefectural Univ, Soja, Japan 9.Peking Univ, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Luo, Weilin,Lu, Jinhu,Li, Xuerong,et al. Rethinking Motivation of Deep Neural Architectures[J]. IEEE CIRCUITS AND SYSTEMS MAGAZINE,2020,20(4):65-76.
APA	Luo, Weilin,Lu, Jinhu,Li, Xuerong,Chen, Lei,&Liu, Kexin.(2020).Rethinking Motivation of Deep Neural Architectures.IEEE CIRCUITS AND SYSTEMS MAGAZINE,20(4),65-76.
MLA	Luo, Weilin,et al."Rethinking Motivation of Deep Neural Architectures".IEEE CIRCUITS AND SYSTEMS MAGAZINE 20.4(2020):65-76.