A New Stability Condition of Discrete Hopfield Neural Networks with Weight Function Matrix

Zhang, Ying; Li, Jun; Ye, Zhengwang

doi:10.1109/fitme.2008.118

Cited by 3 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Particularly when we consider a longterm dynamical behaviors of the system and consider seasonality of the changing environment, the parameters of the system usually will change with time [10]. In resent years, to overcome the deficiencies of the Hopfield network, some experts start working on the stability properties of DHNN that weight matrix changes with time [10][11][12][13]. The stability of HNN that the weight function matrix and the threshold function vector are all same periodic functions is studied [10,11].…”

Section: Introductionmentioning

confidence: 99%

Stability Analysis of Discrete Hopfield Neural Networks with Weighted Function Matrix and Delay

Mao

et al. 2009

2009 Second International Conference on Information and Computing Science

Self Cite

View full text Add to dashboard Cite

In this paper, discrete Hopfield neural networks with weight function matrix(DHNNWFM) and discrete Hopfield neural networks with weight function matrix and delay(DHNNWFMD) are introduced. And the stability properties of DHNNWFMD that weight function matrix is a symmetric function matrix are studied. And we obtain a important result that If the weight function matrix is a symmetric function matrix and delayed matrix is a column diagonally dominant matrix, DHNNWFMD will converge to a state in serial mode. It provides some theory basis for the application of DHNNWFMD.

show abstract

Section: Introductionmentioning

confidence: 99%

Stability Analysis of Discrete Hopfield Neural Networks with Weighted Function Matrix and Delay

Mao

et al. 2009

2009 Second International Conference on Information and Computing Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Unfortunately, most matrixes of DHNN and DHNN with time delay are constant matrixes [1][2][3][4][5][6][7][8][9]. In resent years, to overcome the deficiencies of the Hopfield network, some experts start working on the stability properties of DHNN that weight matrix changes with time [10][11][12][13][14][15]. We research a kind of Discrete Hopfield neural networks with weight function matrix and give some the stability conditions of discrete Hopfield neural networks with weight function matrix(DHNNWFM) [12][13][14][15].…”

Section: Introductionmentioning

confidence: 99%

“…In resent years, to overcome the deficiencies of the Hopfield network, some experts start working on the stability properties of DHNN that weight matrix changes with time [10][11][12][13][14][15]. We research a kind of Discrete Hopfield neural networks with weight function matrix and give some the stability conditions of discrete Hopfield neural networks with weight function matrix(DHNNWFM) [12][13][14][15]. In this paper, we go on our works and extend Theorem 1 and 3 of [5] to discrete Hopfield neural networks with weight function matrix and delay.…”

Section: Introductionmentioning

confidence: 99%

Stability Criterion of Discrete Hopfield Neural Networks with Weighted Function Matrix and one-Delay

Zou

Chen

Lai

2011

AMR

View full text Add to dashboard Cite

In this paper, discrete Hopfield neural networks with weight function matrix(WFM) and delay(DHNNWFMD) are presented. And we obtain an important result that if the WFM is a symmetric function matrix(SFM) and delayed function matrix(DFM) is a diagonally dominant function matrix(DDFM), DHNNWFMD will converge to a state in serial mode and if the WFM is a SFM and non-negative definite function matrix(NFM) and DFM is a DDFM, DHNNWFMD will converge to a state in parallel mode. It provides some theory basis for the application of DHNNWFMD.

show abstract

Stability Analysis of Discrete Hopfield Neural Networks with the Nonnegative Definite Monotone Increasing Weight Function Matrix

Jun

Yong-feng

et al. 2009

Discrete Dynamics in Nature and Society

View full text Add to dashboard Cite

The original Hopfield neural networks model is adapted so that the weights of the resulting network are time varying. In this paper, the Discrete Hopfield neural networks with weight function matrix (DHNNWFM) the weight changes with time, are considered, and the stability of DHNNWFM is analyzed. Combined with the Lyapunov function, we obtain some important results that if weight function matrix (WFM) is weakly (or strongly) nonnegative definite function matrix, the DHNNWFM will converge to a stable state in serial (or parallel) model, and if WFM consisted of strongly nonnegative definite function matrix and column (or row) diagonally dominant function matrix, DHNNWFM will converge to a stable state in parallel model.

show abstract

A New Stability Condition of Discrete Hopfield Neural Networks with Weight Function Matrix

Cited by 3 publications

References 6 publications

Stability Analysis of Discrete Hopfield Neural Networks with Weighted Function Matrix and Delay

Stability Analysis of Discrete Hopfield Neural Networks with Weighted Function Matrix and Delay

Stability Criterion of Discrete Hopfield Neural Networks with Weighted Function Matrix and one-Delay

Stability Analysis of Discrete Hopfield Neural Networks with the Nonnegative Definite Monotone Increasing Weight Function Matrix

Contact Info

Product

Resources

About