Periodic oscillation for discrete-time Hopfield neural networks

2004 ◽  
Vol 329 (3) ◽  
pp. 199-206 ◽  
Author(s):  
Shangjiang Guo ◽  
Lihong Huang
Keyword(s):  
Neural Networks ◽  
Discrete Time ◽  
Periodic Oscillation ◽  
Hopfield Neural Networks

scholarly journals A broad class of discrete-time hypercomplex-valued Hopfield neural networks

2020 ◽  
Vol 122 ◽  
pp. 54-67 ◽  
Author(s):  
Fidelis Zanetti de Castro ◽  
Marcos Eduardo Valle
Keyword(s):  
Neural Networks ◽  
Discrete Time ◽  
Broad Class ◽  
Hopfield Neural Networks

scholarly journals On Global Exponential Stability of Discrete-Time Hopfield Neural Networks with Variable Delays

2007 ◽  
Vol 2007 ◽  
pp. 1-9 ◽  
Author(s):  
Qiang Zhang ◽  
Xiaopeng Wei ◽  
Jin Xu
Keyword(s):  
Neural Networks ◽  
Exponential Stability ◽  
Discrete Time ◽  
Global Exponential Stability ◽  
Stability Result ◽  
Hopfield Neural Networks ◽  
Difference Inequality ◽  
Variable Delays

Global exponential stability of a class of discrete-time Hopfield neural networks with variable delays is considered. By making use of a difference inequality, a new global exponential stability result is provided. The result only requires the delay to be bounded. For this reason, the result is milder than those presented in the earlier references. Furthermore, two examples are given to show the efficiency of our result.

scholarly journals Chaotic Hopfield Neural Network Swarm Optimization and Its Application

2013 ◽  
Vol 2013 ◽  
pp. 1-10 ◽  
Author(s):  
Yanxia Sun ◽  
Zenghui Wang ◽  
Barend Jacobus van Wyk
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Discrete Time ◽  
Optimization Algorithm ◽  
Optimization Problems ◽  
Search Behavior ◽  
Hopfield Neural Network ◽  
Hopfield Neural Networks ◽  
Swarm Optimization ◽  
Continuous State

A new neural network based optimization algorithm is proposed. The presented model is a discrete-time, continuous-state Hopfield neural network and the states of the model are updated synchronously. The proposed algorithm combines the advantages of traditional PSO, chaos and Hopfield neural networks: particles learn from their own experience and the experiences of surrounding particles, their search behavior is ergodic, and convergence of the swarm is guaranteed. The effectiveness of the proposed approach is demonstrated using simulations and typical optimization problems.

Sign in / Sign up

Export Citation Format

Share Document