知识卡片
质心更新使用各簇样本均值
交替执行最近质心分配和各簇样本均值更新,直到变化足够小或达到停止条件。更新不是求几个旧质心的重心,也不是直接用方差当新位置;还需处理空簇等实现边界。
结构图:
flowchart TD
A[当前质心] --> B[每点分配到最近质心]
B --> C[按各簇样本计算均值]
C --> D{达到停止条件}
D -->|否| A
D -->|是| E[输出分组与质心]
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 无监督学习模型
原书出处 · 1 处
- · 查看原书依据
In K-means, we take each point belonging to a given data set and associate it to the nearest centroid. When all points are assigned, the first step is completed, and the initial grouping is done. Next, we recalculate k new centroids as centers of the clusters resulting from the previous step. Once we have the new centroids, a new grouping is to be made between
参考来源
- 位置:《Machine Learning Fundamentals: Concepts, Models, and Applications》第07章《无监督学习模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Machine Learning Fundamentals: Concepts, Models, and Applications/_epub-src/OEBPS/xhtml/20_chapter07.xhtml)
- 结论依据:摘录中关于质心更新使用各簇样本均值的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。
- 原始内容:In K-means, we take each point belonging to a given data set and associate it to the nearest centroid. When all points are assigned, the first step is completed, and the initial grouping is done. Next, we recalculate k new centroids as centers of the clusters resulting from the previous step. Once we have the new centroids, a new grouping is to be made between