Title :
The Research on the GC Property for RNNs with Limited Matrix 2-Norm
Author :
Chen Qiao ; Rui Zhang ; Jing Yao ; Xiangliang Kong ; Changsheng Zhou
Author_Institution :
Sch. of Math. & Stat., Xi´an Jiaotong Univ., Xi´an, China
Abstract :
The global convergence (GC) analysis of recurrent neural networks (RNNs) is a first and necessary step for any practical applications of them. In the present paper, when the connecting matrix of the RNNs with projection mapping owning limited norm, the GC property is assured under the critical condition. The results given here not only improve deeply upon the existing relevant critical as well as non-critical dynamics conclusions in literature, but also can be used in the practical application of RNNs directly.
Keywords :
convergence; matrix algebra; recurrent neural nets; GC property; RNNs; global convergence analysis; limited matrix 2-norm; recurrent neural networks; Analytical models; Biological neural networks; Convergence; Educational institutions; Recurrent neural networks; global convergence; matrix 2-norm; projection mapping; recurrent neural networks;
Conference_Titel :
Intelligent Systems (GCIS), 2013 Fourth Global Congress on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4799-2885-9
DOI :
10.1109/GCIS.2013.19
