Title
Multistability of Switched Neural Networks With Piecewise Linear Activation Functions Under State-Dependent Switching.
Abstract
This paper is concerned with the multistability of switched neural networks with piecewise linear activation functions under state-dependent switching. Under some reasonable assumptions on the switching threshold and activation functions, by using the state-space decomposition method, contraction mapping theorem, and strictly diagonally dominant matrix theory, we can characterize the number of equ...
Year
DOI
Venue
2019
10.1109/TNNLS.2018.2876711
IEEE Transactions on Neural Networks and Learning Systems
Keywords
Field
DocType
Switches,Neural networks,Switched systems,Associative memory,Mathematical model,Learning systems,Matrix decomposition
Topology,Contraction mapping,Pattern recognition,Matrix (mathematics),Computer science,Matrix decomposition,Equilibrium point,Diagonally dominant matrix,Artificial intelligence,Multistability,Artificial neural network,Piecewise linear function
Journal
Volume
Issue
ISSN
30
7
2162-237X
Citations 
PageRank 
References 
7
0.40
28
Authors
3
Name
Order
Citations
PageRank
Zhenyuan Guo1898.75
Linlin Liu2140.81
Jun Wang39228736.82