开发者:上海品职教育科技有限公司 隐私政策详情

应用版本:4.2.11(IOS)|3.2.5(安卓)APP下载

金融民工阿聪 · 2021年05月01日

关于SVM

NO.PZ2016082405000014

问题如下:

Using the properties of firms that have already fallen into default/non-default groups to categorize a new observation by how closely it resembles the members already in each of the groups is referred to as:

选项:

A.

linear discriminant analysis.

B.

the k-nearest neighbor approach.

C.

support vector machines.

D.

None of the above.

解释:

The K-nearest neighbor is a nonparametric discriminant technique that uses the properties of firms that already have fallen into the categories of interest, and it categorizes a new entrant by how close it resembles the members already in each of the groups.

嗨,从没放弃的小努力你好:


一个圈内有多少好的和坏的,圈的大小也就意味着一定远近程度的范围内啦。

支持向量机主要还是要分类,没有突出一个点和其他的距离说法。

----------------------------------------------

加油吧,让我们一起遇见更好的自己!

之前老师回复如上↑

有个问题,就是SVM在算的时候,不就是为了找到一个最佳的那个界限,所以会引入距离最短的定义吗?为什么说没有突出一个点和其他的距离说法。

1 个答案

袁园_品职助教 · 2021年05月02日

K-nearest neighbour 就是以点为中心画个圈

SVM 是画一条线区分开,这条线画在最短距离的位置

用图片可能更直观一些


K-Nearest Neighbor with Practical Implementation | by Amir Ali | Wavy AI  Research Foundation | Medium


Support Vector Machines Tutorial - Learn to implement SVM in Python -  DataFlair