Multistability of Neural Networks With Mexican-Hat-Type Activation Functions

doi:10.1109/TNNLS.2012.2210732

CORC > 上海财经大学 > 上海财经大学

	Multistability of Neural Networks With Mexican-Hat-Type Activation Functions
	Wang, Lili 1; Chen, Tianping 2
刊名	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2012-11
卷号	23 期号:11 页码:1816-1826
关键词	Attraction basin Mexican-hat activation multistability neural networks stability analysis
ISSN号	2162-237X
DOI	10.1109/TNNLS.2012.2210732
英文摘要	In this paper, we are concerned with a class of neural networks with Mexican-hat-type activation functions. Due to the different structure from neural networks with saturated activation functions, a set of new sufficient conditions are presented to study the multistability, including the total number of equilibrium points, their locations, and stability. Furthermore, the attraction basins of stable equilibrium points are investigated for two-neuron neural networks. The investigation shows that the stable manifolds of unstable equilibrium points constitute the boundaries of attraction basins of stable equilibrium points. Several illustrative examples are given to verify the effectiveness of our results.
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000310370300012
内容类型	期刊论文
源URL	[http://10.2.47.112/handle/2XS4QKH4/2089]
专题	上海财经大学
通讯作者	Wang, Lili
作者单位	1.Shanghai Univ Finance & Econ, Dept Appl Math, Shanghai 200433, Peoples R China; 2.Fudan Univ, Sch Math Sci, Chinese Minist Educ, Key Lab Nonlinear Sci, Shanghai 200433, Peoples R China
推荐引用方式 GB/T 7714	Wang, Lili,Chen, Tianping. Multistability of Neural Networks With Mexican-Hat-Type Activation Functions[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2012,23(11):1816-1826.
APA	Wang, Lili,&Chen, Tianping.(2012).Multistability of Neural Networks With Mexican-Hat-Type Activation Functions.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,23(11),1816-1826.
MLA	Wang, Lili,et al."Multistability of Neural Networks With Mexican-Hat-Type Activation Functions".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 23.11(2012):1816-1826.