Please use this identifier to cite or link to this item:
|Title:||Multistability of discrete-time recurrent neural networks with unsaturating piecewise linear activation functions|
Recurrent neural networks
Unsaturating piecewise linear activation functions
|Source:||Yi, Z., Tan, K.K. (2004-03). Multistability of discrete-time recurrent neural networks with unsaturating piecewise linear activation functions. IEEE Transactions on Neural Networks 15 (2) : 329-336. ScholarBank@NUS Repository. https://doi.org/10.1109/TNN.2004.824272|
|Abstract:||This paper studies the multistability of a class of discrete-time recurrent neural networks with unsaturating piecewise linear activation functions. It addresses the nondivergence, global attractivity, and complete stability of the networks. Using the local inhibition, conditions for nondivergence are derived, which not only guarantee nondivergence, but also allow for the existence of multiequilibrium points. Under these nondivergence conditions, global attractive compact sets are obtained. Complete stability is studied via constructing novel energy functions and using the well-known Cauchy Convergence Principle. Examples and simulation results are used to illustrate the theory.|
|Source Title:||IEEE Transactions on Neural Networks|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Feb 21, 2018
WEB OF SCIENCETM
checked on Dec 13, 2017
checked on Feb 24, 2018
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.