简体   繁体   English

在templateSVM中为RBF内核设置伽马值

[英]Setting gamma value for RBF kernel in templateSVM

According to this document (and several others), the RBF kernel is defined by the equation below, and can be adjusted by varying the parameters C and gamma. 根据该文档 (和其他几个文档 ),RBF内核由以下方程式定义,并且可以通过更改参数C和伽马来进行调整。 在此处输入图片说明

The documentation for svmTemplate defines the RBF kernel without a gamma value as shown below. svmTemplate文档定义了不带gamma值的RBF内核,如下所示。

在此处输入图片说明

Why does svmTemplate not use gamma? 为什么svmTemplate不使用伽玛? Is there a way of specifying it? 有没有指定方法?

I'm guessing it is because it is essentially rolled into the "KernelScale" option in the documentation. 我猜这是因为它实际上已卷入文档中的“ KernelScale”选项。 It indicates that it divides all the values in the data by a constant, which allows you to essentially set the gamma parameter that way. 它表示已将数据中的所有值除以一个常数,从而使您可以本质上以这种方式设置gamma参数。 You can see that ||x z-y z|| 您可以看到|| x z-y z || = ||xy||*z, and so obtains the equivalent impact (so long as you select the KernelScale value appropriately). = || xy || ** z,因此可以获得等效的影响(只要您适当选择KernelScale值)。 The documentation says the scale is selected heuristically by default, and there do exist heuristics for the RBF kerne's parameters. 该文档说,秤默认情况下是通过试探法选择的,并且对于RBF kerne参数确实存在试探法。

It's not the way I would have coded such a system, but it should work. 这不是我编写这种系统的方式,但是应该可以。

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM