Open AccessExponential Stability for the Neutral-type Inertial BAM Neural Networks with Time-varying Delays
Author(s) -
Jenjira Thipcha,
Sirada Pinjai
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1850/1/012116
Subject(s) - control theory (sociology) , artificial neural network , weighting , inertial frame of reference , stability (learning theory) , type (biology) , exponential stability , bidirectional associative memory , mathematics , matrix (chemical analysis) , computer science , control (management) , nonlinear system , physics , artificial intelligence , content addressable memory , ecology , quantum mechanics , machine learning , acoustics , biology , materials science , composite material
In this paper, the global exponential stability for the neutral-type inertial bidirectional association memory neural networks with time-varying delays is considered. In our study, the lower and upper bounds of the activation functions are allowed to be either positive, negative or zero. By constructing new and improved Lyapunov-Krasovskii functional and introducing free-weighting matrices, a new and improved delay-dependent the neutral-type inertial bidirectional association memory neural networks with time-varying delays is derived in the form of linear matrix.