Analysis and synthesis of a class of discrete-time neural networks described on hypercubes

Michel, Anthony N.; Si, Jennie; Yen, Gary G.

doi:10.1109/iscas.1990.112175

Cited by 16 publications

(30 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Let A be a real n x n matrix, A -an interval matrix containing A, and A -, A + , A 0 and R A -the left end, the right end, the center and the radius of A, respectively (throughout the paper, bold face letters will be used to denote interval quantities while ordinary letters will stand for their non-interval counterparts). (8) where matrix H has the same structure defined by (5). It is seen from (8) that matrix Q is implicit function of A.…”

Section: Problem Statementmentioning

confidence: 99%

“…First, we check condition (2) , (50) where matrix H II satisfies (4). We compute matrices H (according to (5)) and…”

Section: Stability Of the Central Problem Stability Analysis Of Systementioning

confidence: 99%

“…It is well known that the model of discrete-time dynamical systems with partial state saturation is [1]: This general model describes also the discrete-time neural networks [5] working on hypercube. This type of nonlinear systems have been investigated by many researchers (see e.g.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Interval criterion for stability analysis of discrete-time nonlinear systems with partial state saturation nonlinearities

2006

View full text Add to dashboard Cite

A generalization of sufficient conditions for global asymptotic stability of the equilibrium 0 = e x of discrete-time neural networks described by systems which have saturation nonlinearities on part of the states in the case of interval uncertainties is considered. When using quadratic form Lyapunov functions, sufficient conditions based on the positive definite interval matrices are presented. In order to check this a recent proposed method for determining the outer bounds of eigenvalues ranges is used. A numerical example illustrating the applicability of the method suggested is solved in the end of the paper.

show abstract

Section: Problem Statementmentioning

confidence: 99%

“…First, we check condition (2) , (50) where matrix H II satisfies (4). We compute matrices H (according to (5)) and…”

Section: Stability Of the Central Problem Stability Analysis Of Systementioning

confidence: 99%

See 1 more Smart Citation

Interval criterion for stability analysis of discrete-time nonlinear systems with partial state saturation nonlinearities

2006

View full text Add to dashboard Cite

show abstract

“…A storage algorithm that utilizes the eigenstructure method [8] is used for specifying the appropriate T and I parameter values that guarantee that patterns of concepts' combinations are stored as equilibrium points of the RSN (see [8] for a description of the algorithm). When two or more concepts are active in a pattern, i.e.…”

Section: The Connectionist Implementationmentioning

confidence: 99%

“…an equilibrium point. Thus, the RSN performs associate inference depending on the input pattern and, unlike the general use of an associative memory, it operates synchronously: (i) it updates the states of its nodes simultaneously, and (ii) the input pattern is kept unchanged until convergence of the network (see [8] for details on the network operation).…”

Section: The Connectionist Implementationmentioning

confidence: 99%

A Connectionist Approach for Supporting Personalized Learning in a Web-Based Learning Environment

Papanikolaou¹,

Magoulas

Grigoriadou³

2000

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The paper investigates the use of computational intelligence for adaptive lesson presentation in a Web-based learning environment. A specialized connectionist architecture is developed and a formulation of the planning strategy retrieval in the context of the network dynamics is proposed to select the content of the lesson in a goal-oriented way of 'teaching'. The educational material of the course is stored in a connectionist-based distributed information storage system that provides capabilities for optimal selection of the educational material according to the knowledge needs, abilities and preferences of each learner. Low-level tests of the system have been performed to investigate how the connectionist architecture and the learner model function together to create an operational learning environment. Preliminary experiments indicate that personalized content delivery is provided in an educational effective way.

show abstract

Observer‐based H_∞ control for systems with repeated scalar nonlinearities and multiple packet losses

Dong

Wang

Gao

2010

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

SUMMARYThis paper is concerned with the H ∞ control problem for a class of systems with repeated scalar nonlinearities and multiple missing measurements. The nonlinear system is described by a discrete-time state equation involving a repeated scalar nonlinearity, which typically appears in recurrent neural networks. The measurement missing phenomenon is assumed to occur, simultaneously, in the communication channels from the sensor to the controller and from the controller to the actuator, where the missing probability for each sensor/actuator is governed by an individual random variable satisfying a certain probabilistic distribution in the interval [0 1]. Attention is focused on the analysis and design of an observer-based feedback controller such that the closed-loop control system is stochastically stable and preserves a guaranteed H ∞ performance. Sufficient conditions are obtained for the existence of admissible controllers. It is shown that the controller design problem under consideration is solvable if certain linear matrix inequalities (LMIs) are feasible. Three examples are provided to illustrate the effectiveness of the developed theoretical results.

show abstract

Analysis and synthesis of a class of discrete-time neural networks described on hypercubes

Cited by 16 publications

References 11 publications

Interval criterion for stability analysis of discrete-time nonlinear systems with partial state saturation nonlinearities

Interval criterion for stability analysis of discrete-time nonlinear systems with partial state saturation nonlinearities

A Connectionist Approach for Supporting Personalized Learning in a Web-Based Learning Environment

Observer‐based H_∞ control for systems with repeated scalar nonlinearities and multiple packet losses

Contact Info

Product

Resources

About

Analysis and synthesis of a class of discrete-time neural networks described on hypercubes

Cited by 16 publications

References 11 publications

Interval criterion for stability analysis of discrete-time nonlinear systems with partial state saturation nonlinearities

Interval criterion for stability analysis of discrete-time nonlinear systems with partial state saturation nonlinearities

A Connectionist Approach for Supporting Personalized Learning in a Web-Based Learning Environment

Observer‐based H∞ control for systems with repeated scalar nonlinearities and multiple packet losses

Contact Info

Product

Resources

About

Observer‐based H_∞ control for systems with repeated scalar nonlinearities and multiple packet losses