Abstract | ||
---|---|---|
In this paper, a penalty term is added to the conventional error function to improve the generalization of the Ridge Polynomial neural network. In order to choose appropriate learning parameters, we propose a monotonicity theorem and two convergence theorems including a weak convergence and a strong convergence for the synchronous gradient method with penalty for the neural network. The experimental results of the function approximation problem illustrate the above theoretical results are valid. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1016/j.neucom.2012.05.022 | Neurocomputing |
Keywords | Field | DocType |
Ridge Polynomial neural network,Gradient algorithm,Monotonicity,Convergence | Convergence (routing),Gradient method,Weak convergence,Mathematical optimization,Normal convergence,Compact convergence,Convergence tests,Artificial intelligence,Artificial neural network,Machine learning,Mathematics,Modes of convergence | Journal |
Volume | Issue | ISSN |
97 | null | 0925-2312 |
Citations | PageRank | References |
2 | 0.37 | 6 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xin Yu | 1 | 8 | 3.18 |
Qingfeng Chen | 2 | 25 | 6.74 |