Title | ||
---|---|---|
Solving Quadratic Minimization Problem By Finite-Time Recurrent Neural Network Using Two Different Nonlinear Activation Functions |
Abstract | ||
---|---|---|
Two finite-time recurrent neural network models (abbreviated as FTRNN-1 model and FTRNN-2 model) are proposed and investigated for solving quadratic minimization problem that is widely used in practical engineering applications. Different from the original recurrent neural network (ORNN) for quadratic minimization, both FTRNN-1 model and FTRNN-2 model respectively possess a nonlinear activation function, and thus have finite-time convergence performance. Simulative results validate the efficiency and the high accuracy of the proposed two models for handling quadratic minimization problems, as compared with the ORNN model. |
Year | Venue | Keywords |
---|---|---|
2018 | PROCEEDINGS OF 2018 TENTH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTATIONAL INTELLIGENCE (ICACI) | quadratic minimization, recurrent neural network, nonlinear activation fitnction, finite-time convergence |
Field | DocType | Citations |
Minimization problem,Convergence (routing),Applied mathematics,Nonlinear system,Activation function,Computer science,Quadratic equation,Recurrent neural network,Minification,Finite time | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yongsheng Zhang | 1 | 204 | 43.58 |
Lin Xiao | 2 | 562 | 42.84 |
Bolin Liao | 3 | 281 | 18.70 |
Lei Ding | 4 | 142 | 26.77 |
Rongbo Lu | 5 | 101 | 5.12 |