| 谢富强,唐耀庚.多层前向神经网络权值初始化的研究进展[J].南华大学学报(自然科学版),2006,20(3):98~101.[.The Development of Weight Initialization Methods for MFN[J].Journal of University of South China(Science and Technology),2006,20(3):98~101.] |
| 多层前向神经网络权值初始化的研究进展 |
| The Development of Weight Initialization Methods for MFN |
| 修订日期：2006-06-13 |
| DOI： |
| 中文关键词: 多层前向神经网络 权值初始化 泛化能力 |
| 英文关键词:Neural network,multilayer feedforward network,weight initialization,generalization ability |
| 基金项目: |
| 谢富强 唐耀庚 |
| 南华大学计算机科学与技术学院,湖南衡阳421001 |
| 摘要点击次数: 682 |
| 全文下载次数: 3 |
| 中文摘要: |
| 理想的初始值可以使多层前向网络模型有较快的收敛速度，同时避免陷入局部最小．对现有多种前向网络的权值初始化方法进行了综述，最后提出了若干待研究的问题． |
| 英文摘要: |
| Proposed initialization methods which are shown to achieve very fast learning speed and to decrease the probability of local minima are suggested.In this paper,the recent developments of initialization of multilayer feedforward neural networks are surveyed.Finally,the major problems and research trends are pointed out. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |