Theory of Monte Carlo sampling-based Alopex algorithms for neural networks
Theory of Monte Carlo sampling-based Alopex algorithms for neural networks
复制标题
基于蒙特卡罗采样的神经网络 Alopex 算法理论
DOI：
--
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
S. Becker
中科院分区：
文献类型：
--
作者：
Zhe Chen;S. Haykin;S. Becker
我们提出了两个新的Monte Carlo抽样为基础的Alopex（AL出租米的模式提取）算法训练神经网络。所提出的算法自然结合了联合收割机的顺序蒙特卡罗估计和Alopex类梯度无优化过程，和学习过程中的递归贝叶斯估计框架。对各种问题的实验结果显示了令人鼓舞的收敛结果。
We propose two novel Monte Carlo sampling-based Alopex (ALgorithm Of Pattern EXtraction) algorithms for training neural networks. The proposed algorithms naturally combine the sequential Monte Carlo estimation and Alopex-like procedure for gradient-free optimization, and the learning proceeds within the recursive Bayesian estimation framework. Experimental results on various problems show encouraging convergence results.