Trainable back-propagated functional transfer matrices

doi:10.1007/s10489-018-1266-3

	Trainable back-propagated functional transfer matrices
	Cai, Cheng-Hao 1; Xu, Yanyan 2; Ke, Dengfeng3 ; Su, Kaile 4; Sun, Jing 1
发表期刊	APPLIED INTELLIGENCE
ISSN	0924-669X
	2019-02-01
卷号	49 期号:2 页码:376-395
通讯作者	Xu, Yanyan(xuyanyan@bjfu.edu.cn)
摘要	Functional transfer matrices consist of real functions with trainable parameters. In this work, functional transfer matrices are used to model functional connections in neural networks. Different from linear connections in conventional weight matrices, the functional connections can represent nonlinear relations between two neighbouring layers. Neural networks with the functional connections, which are called functional transfer neural networks, can be trained via back-propagation. On the two spirals problem, the functional transfer neural networks are able to show considerably better performance than conventional multi-layer perceptrons. On the MNIST handwritten digit recognition task, the performance of the functional transfer neural networks is comparable to that of the conventional model. This study has demonstrated that the functional transfer matrices are able to perform better than the conventional weight matrices in specific cases, so that they can be alternatives of the conventional ones.
关键词	Functional transfer neural networks Functional connections Back-propagation
DOI	10.1007/s10489-018-1266-3
关键词[WOS]	LINK NEURAL-NETWORK ; NEURONS
收录类别	SCI
语种	英语
资助项目	Fundamental Research Funds for the Central Universities[2016JX06] ; National Natural Science Foundation of China[61472369] ; Fundamental Research Funds for the Central Universities[2016JX06] ; National Natural Science Foundation of China[61472369]
项目资助者	Fundamental Research Funds for the Central Universities ; National Natural Science Foundation of China
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000457362600005
出版者	SPRINGER
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/25276
专题	多模态人工智能系统全国重点实验室_智能交互
通讯作者	Xu, Yanyan
作者单位	1.Univ Auckland, Dept Comp Sci, 38 Princes St, Auckland 1142, New Zealand 2.Beijing Forestry Univ, Sch Informat Sci & Technol, 35 East Qinghua Rd, Beijing 100083, Peoples R China 3.Chinese Acad Sci, Inst Automat, 95 East Zhongguancun Rd, Beijing 100190, Peoples R China 4.Griffith Univ, Sch Informat & Commun Technol, 170 Kessels Rd, Brisbane, Qld 4111, Australia
推荐引用方式 GB/T 7714	Cai, Cheng-Hao,Xu, Yanyan,Ke, Dengfeng,et al. Trainable back-propagated functional transfer matrices[J]. APPLIED INTELLIGENCE,2019,49(2):376-395.
APA	Cai, Cheng-Hao,Xu, Yanyan,Ke, Dengfeng,Su, Kaile,&Sun, Jing.(2019).Trainable back-propagated functional transfer matrices.APPLIED INTELLIGENCE,49(2),376-395.
MLA	Cai, Cheng-Hao,et al."Trainable back-propagated functional transfer matrices".APPLIED INTELLIGENCE 49.2(2019):376-395.