Pattern Learning by Functional-Differential Neural Networks with Arbitrary Path Weights

1982 ◽  
pp. 157-193 ◽  
Author(s):  
Stephen Grossberg
Keyword(s):  
Neural Networks ◽  
Pattern Learning ◽  
Functional Differential

scholarly journals Type-K Exponential Ordering with Application to Delayed Hopfield-Type Neural Networks

2012 ◽  
Vol 2012 ◽  
pp. 1-9
Author(s):  
Bin-Guo Wang
Keyword(s):  
Neural Networks ◽  
Differential Equations ◽  
Functional Differential Equations ◽  
Type K ◽  
Functional Differential ◽  
Quasimonotone Condition

Order-preserving and convergent results of delay functional differential equations without quasimonotone condition are established under type-K exponential ordering. As an application, the model of delayed Hopfield-type neural networks with a type-K monotone interconnection matrix is considered, and the attractor result is obtained.

STABILITY ANALYSIS FOR DELAYED CELLULAR NEURAL NETWORKS BASED ON LINEAR MATRIX INEQUALITY APPROACH

2004 ◽  
Vol 14 (09) ◽  
pp. 3377-3384 ◽  
Author(s):  
XIAOFENG LIAO ◽  
KWOK-WO WONG ◽  
SHIZHONG YANG
Keyword(s):  
Neural Networks ◽  
Linear Matrix Inequality ◽  
Functional Differential Equations ◽  
Sufficient Conditions ◽  
Cellular Neural Networks ◽  
Linear Matrix ◽  
Matrix Inequality ◽  
Linear Matrix Inequality Approach ◽  
Functional Differential ◽  
The Stability

Some sufficient conditions for the asymptotic stability of cellular neural networks with time delay are derived using the Lyapunov–Krasovskii stability theory for functional differential equations as well as the linear matrix inequality (LMI) approach. The analysis shows how some well-known results can be refined and generalized in a straightforward manner. Moreover, the stability criteria obtained are delay-independent. They are less conservative and restrictive than those reported so far in the literature, and provide a more general set of criteria for determining the stability of delayed cellular neural networks.

scholarly journals Abstract Rule Based Pattern Learning with Neural Networks

2020 ◽  
Vol 34 (10) ◽  
pp. 13718-13719
Author(s):  
Radha Manisha Kopparti
Keyword(s):  
Neural Networks ◽  
Research Work ◽  
Pattern Learning ◽  
Rule Based ◽  
Abstract Rule

In this research work, the problem of learning abstract rules using neural networks is studied and a solution called ‘Relation Based Patterns’ (RBP) which model abstract relationships based on equality is proposed.

GLOBAL ROBUST STABILITY ANALYSIS FOR NEURAL NETWORKS WITH CONSTANT OR VARIABLE DELAYS

2010 ◽  
Vol 24 (03) ◽  
pp. 335-355
Author(s):  
HUI WANG ◽  
CHUANDONG LI ◽  
HONGBING XU
Keyword(s):  
Neural Networks ◽  
Functional Differential Equations ◽  
Linear Matrix ◽  
Variable Delays ◽  
Robust Stability Analysis ◽  
Global Robust Asymptotic Stability ◽  
Functional Differential ◽  
Asymptotical Convergence ◽  
Robust Asymptotic Stability ◽  
New Criteria

In this paper, some criteria are derived for global robust asymptotic stability of a class of interval neural networks with multiple constant or time-varying delays via the Lyapunov–Krasovskii stability theory for functional differential equations and the linear matrix inequality (LMI) approach. The main results are applied to the uncertain systems with single delay, and several new criteria to determine the asymptotical convergence of these systems are obtained. Numerical examples are also given to show the effectiveness of our results.

Sign in / Sign up

Export Citation Format

Share Document