期刊文献+

神经网络训练中的迭代扩展卡尔曼粒子滤波算法 被引量:1

Iterated Extended Kalman Particle Filter for Neural Network Training
下载PDF
导出
摘要 基本粒子滤波算法已被成功用于训练神经网络,但该算法在建议分布的选择上并没有考虑当前时刻观测值的影响,针对该问题提出在神经网络训练中,使用迭代扩展卡尔曼滤波器来生成建议分布.由于迭代扩展卡尔曼滤波器在传递近似建议分布的均值和协方差的过程中,充分利用了观测值信息,从而可以更好地描述神经网络权值的后验概率分布.实验结果表明,在训练神经网络时,迭代扩展卡尔曼滤波器作为建议分布的粒子滤波算法训练性能明显优于基本粒子滤波算法及扩展卡尔曼粒子滤波算法(EKPF). The generic particle filter has been applied with success to neural network training, but the proposal distribution chosen by the generic particle filter doesn't incorporate the latest observations which can deteriorate the performance of the algorithm. In this paper, we propose to use the iterated extended Kalman filter to generate proposal distribution in particle filtering framework. The iterated extended Kalman filter can make efficient use of the latest observation, and the generated proposal distribution can approximate the posterior distribution of neural network weights much better and improve the performance of particle filter. The experimental results show that the proposed particle filter outperforms the generic particle filter and the EKPF.
作者 张应博
出处 《微电子学与计算机》 CSCD 北大核心 2010年第8期103-107,共5页 Microelectronics & Computer
关键词 神经网络训练 迭代扩展卡尔曼滤波 迭代扩展卡尔曼粒子滤波 neural network training iterated extended Kalman filter iterated extended Kalman particle filter
  • 相关文献

参考文献8

  • 1Singhal S, Wu L. Training multilayer perceptrons with the extended kalman algorithrn[J ]. Advance in Neural Information Processing Systems, 1998(1):133- 140.
  • 2Freitas J F G, Johnson S E, Niranjan M, et al. Global optimization of neural network models via sequential sampling - importance resampling[C]//Proc, of the 5th International Conference on Spoken Language Processing. Sydney, Australia, 1998.
  • 3于金霞,汤永利,刘文静.粒子滤波自适应机制研究综述[J].计算机应用研究,2010,27(2):417-422. 被引量:8
  • 4Arulampalam M S, Maskell S, Gordon N, et al. A tutorial on particle filters for on - line nonlinear/non - gaussian bayesian tracking[ J ]. IEEE Transactions on signal processing, 2002, 50(2) : 174 - 188.
  • 5Doueet A, Godsill S, Andrieu C. On sequential monte carlo sampling methods for bayesian filtering[J ]. Statistics and Computing, 2000(10) : 197 - 208.
  • 6Cappe O, Godsill S J, Moulines E. An overview of existing methods and recent advances in sequential monte carlo[J ]. Proceedings of the IEEE, 2007, 95(5):899- 924.
  • 7王法胜,郭权.基于扩展卡尔曼粒子滤波算法的神经网络训练[J].计算机工程与科学,2010,32(5):48-50. 被引量:10
  • 8李良群,姬红兵,罗军辉.迭代扩展卡尔曼粒子滤波器[J].西安电子科技大学学报,2007,34(2):233-238. 被引量:60

二级参考文献61

共引文献73

同被引文献8

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部