Title :
A new stability condition for discrete time recurrent neural networks with complex-valued linear threshold neurons
Author :
Wei Zhou ; Zurada, Jacek M.
Author_Institution :
Coll. of Comput. Sci. & Technol., Southwest Univ. for Nat., Chengdu, China
Abstract :
This paper discusses the stability condition for discrete time recurrent neural networks (RNNs) with complex-valued linear threshold (CLT) neurons. The energy-function method is very useful for complex-valued RNNs study, especially for multi-stable RNNs. In addition to properties of CLT RNNs discussed in earlier work, a new stability condition is offered here by virtue of a lower-bounded energy function. Simulation results are presented to illustrate the theory.
Keywords :
discrete time systems; recurrent neural nets; stability; CLT; complex-valued RNN; complex-valued linear threshold neurons; discrete time recurrent neural networks; energy-function method; stability condition; Biological neural networks; Educational institutions; Neurons; Recurrent neural networks; Stability analysis; Symmetric matrices; Trajectory;
Conference_Titel :
Neural Networks (IJCNN), 2014 International Joint Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4799-6627-1
DOI :
10.1109/IJCNN.2014.6889621
