问题描述
根据Azure ML Studio文档
Hi, According to azure ML Studio documentation
```
打开模块属性，然后对于重采样方法，选择用于创建单个树的方法.您可以选择装袋或复制.
Open the module properties, and for Resampling method, choose the method used to create the individual trees. You can choose from Bagging or Replicate.
装袋:装袋也称为引导聚合.回归决策林中的每棵树都通过预测输出高斯分布.聚合是要找到一个高斯 它的前两个时刻与高斯混合的时刻相吻合，高斯混合的时刻是通过合并单个树返回的所有高斯而得出的.
Bagging: Bagging is also called bootstrap aggregating. Each tree in a regression decision forest outputs a Gaussian distribution by way of prediction. The aggregation is to find a Gaussian whose first two moments match the moments of the mixture of Gaussians given by combining all Gaussians returned by individual trees.
复制:在复制中，每棵树都在完全相同的输入数据上训练.对于每个树节点使用哪个分割谓词的确定仍然是随机的，并且树将是多样的.
Replicate: In replication, each tree is trained on exactly the same input data. The determination of which split predicate is used for each tree node remains random and the trees will be diverse.
有关使用复制 选项
For more information about the training process with the Replicate option
```
根据上述说明，袋果树的生成方式为:回归决策林中的每棵树都输出高斯 通过预测进行分布.
Based on the above explanation, Bagging tree generation is: Each tree in a regression decision forest outputs a Gaussian distribution by way of prediction.
以及如何复制?它用来预测什么?是否像其他回归林树一样使用标准偏差减少?
推荐答案
感谢您的反馈.
您可以参考我们的研究资源:
You can refer to our research resource :
用于计算机视觉和医学图像分析的决策林. Criminisi和J. Shotton. Springer 2013 ;
https://docs.microsoft.com/zh-CN/azure/machine-learning/studio-module-reference/multiclass-decision -forest#tips
https://docs.microsoft.com/en-us/azure/machine-learning/studio-module-reference/multiclass-decision-forest#tips
此致
雨桐
这篇关于决策森林回归模块中装袋与复制之间的树生成的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！