Training of a class of recurrent neural networks

Author

Shaaban, Khaled M.

Author_Institution

Dept. of Electr. & Comput. Eng., Assiut Univ., Egypt

Volume

3

fYear

1998

Firstpage

78

Abstract

This paper presents design and analysis of a modified version of the Hopfield network which is called a Cascade Recurrent Network (CRN). This network has a single or multilayer feedforward (FF) structure with synchronous input-output feedback. System dynamics are determined by the characteristics of this FF structure. First, a formal definition of the mapping generalization is provided. Using this definition, and the classical definition of stability, the mapping-stability relation is developed in the form of a correspondence between CRN stability properties and FF mapping characteristics. On the basis of this stability-mapping relation, a new synthesis technique is developed

Keywords

cascade networks; feedback; feedforward neural nets; learning (artificial intelligence); recurrent neural nets; stability; Hopfield network modification; cascade recurrent network; feedforward structure; mapping generalization; mapping-stability relation; recurrent neural networks; stability properties; synchronous input-output feedback; synthesis technique; system dynamics; Associative memory; Asymptotic stability; Computer networks; Delay effects; Network synthesis; Neurons; Nonhomogeneous media; Nonlinear dynamical systems; Nonlinear equations; Recurrent neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1998. ISCAS '98. Proceedings of the 1998 IEEE International Symposium on

Conference_Location

Monterey, CA

Print_ISBN

0-7803-4455-3

Type

conf

DOI

10.1109/ISCAS.1998.703902

Filename

703902