| A Second Order Training Algorithm for Multilayer Feedforward Neural Networks |
| |
| 作者姓名： | 谭营 何振亚 邓超 |
| |
| 作者单位： | Tan Ying(谭营) He Zhenya(何振亚) (Department of Radio Engineering，Southeast University，Nanjing 210018)Deng Chao(邓超)(Department of Computer Science，University of Science and Technology of China，Hefei 230026) |
| |
| 摘 要： | ＡＳｅｃｏｎｄＯｒｄｅｒＴｒａｉｎｉｎｇＡｌｇｏｒｉｔｈｍｆｏｒＭｕｌｔｉｌａｙｅｒＦｅｅｄｆｏｒｗａｒｄＮｅｕｒａｌＮｅｔｗｏｒｋｓＴａｎＹｉｎｇ（谭营）ＨｅＺｈｅｎｙａ（何振亚）（ＤｅｐａｒｔｍｅｎｔｏｆＲａｄｉｏＥｎｇｉｎｅｅｒｉｎｇ，Ｓｏｕ...
|
A Second Order Training Algorithm for Multilayer Feedforward Neural Networks |
| |
| Tan Ying.A Second Order Training Algorithm for Multilayer Feedforward Neural Networks[J].Journal of Southeast University(English Edition),1997(1). |
| |
| Authors: | Tan Ying |
| |
| Abstract: | According to the adjusting principle, we propose a second order training algorithm for multilayer feedforward neural network after analyzing the slow convergence reason of traditional BP algorithm. The better region of the learning factors for this proposed algorithm to achieve good learning performance is also given. A computer simulation experiment on XOR problem demonstrates the correctness of our theoretical analysis and the effectiveness of the proposed algorithm. In our experiment, the training progress of the proposed algorithm is about 50 and 20 times faster than the standard BP algorithm and the momentum BP algorithm, respectively. |
| |
| Keywords: | multilayer feedforward neural networks second order training algorithm BP algorithm learning factors XOR problem |
| 本文献已被 CNKI 等数据库收录！ |
