New stability conditions for Hopfield networks in partial simultaneous update mode
IEEE Transactions on Neural Networks
High-order neural network structures for identification of dynamical systems
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
Most matrixes of Discrete Hopfield neural networks(DHNNs) and DHNNs with delay are constant matrixes. However, most weight matrixes of DHNNses are variable in many realistic systems. So, the weight matrix and the threshold vector with time factor are considered, and DHNNs with weight function matrix (DHNNWFM) is described. Moreover, the result that if weight function matrix and threshold function vector respectively converge to a constant matrix and a constant vector that the corresponding DHNNs is stable or the weight matrix function is a symmetric function matrix, then DHNNWFM is stable, is obtained by matrix analysis.