Name
Abstract | ||
|---|---|---|
For purpose of solving system of linear equations (SoLE) more efficiently, a fast convergent gradient neural network (FCGNN) model is designed and discussed in this paper. Different from the design of the conventional gradient neural network (CGNN), the design of the FCGNN model is based on a nonlinear activation function, and thus the better convergence speed can be reached. In addition, the convergence upper bound of the FCGNN model is estimated and provided in details. Simulative results validate the superiority of the FCGNN model, as compared to the CGNN model for finding SoLE. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1016/j.ipl.2018.10.004 | Information Processing Letters |
Keywords | Field | DocType |
Systems of linear equations (SoLE),Fast convergence,Nonlinear activation function,Gradient neural network (GNN),Performance evaluation | Convergence (routing),Discrete mathematics,Applied mathematics,Nonlinear system,System of linear equations,Activation function,Upper and lower bounds,Artificial neural network,Mathematics | Journal |
Volume | ISSN | Citations |
142 | 0020-0190 | 3 |
PageRank | References | Authors |
0.38 | 19 | 8 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lin Xiao | 1 | 94 | 15.07 |
| Kenli Li | 2 | 67 | 12.56 |
| Zhiguo Tan | 3 | 7 | 1.78 |
| Zhijun Zhang | 4 | 286 | 31.45 |
| Bolin Liao | 5 | 281 | 18.70 |
| Ke Chen | 6 | 585 | 36.13 |
| Long Jin | 7 | 537 | 28.68 |
| Shuai Li | 8 | 1278 | 82.46 |