Coursera, Machine Learning, Unsupervised Learning, K-means, Dimentionality Reduction

Clustering

 K-means:
基本思想是先随机选择要分类数目的点,然后找出距离这些点最近的training data 着色,距离哪个点近就算哪种类型,再对每种分类算出平均值,把中心点移动到平均值处,重复着色算平均值,直到分类成功.
  Coursera, Machine Learning, Unsupervised Learning,  K-means, Dimentionality Reduction
  Coursera, Machine Learning, Unsupervised Learning,  K-means, Dimentionality Reduction
 
为了防止k-means 算法得到的是local optima, 可以多次运行k-means, 然后选取得到J最小值的那次初始化方法.
  Coursera, Machine Learning, Unsupervised Learning,  K-means, Dimentionality Reduction
 
 
One way to choose K is elbow method
Coursera, Machine Learning, Unsupervised Learning,  K-means, Dimentionality Reduction
 

Dimentionality Reduction

 
Dimentionality Reduction: 1. data compression to save space of memory and speed up compute. 2. 还有一个作用是可以用降维来visualize data.
 
Coursera, Machine Learning, Unsupervised Learning,  K-means, Dimentionality Reduction
 
降维最常用的算法PCA (Principal Component Analysis)
Coursera, Machine Learning, Unsupervised Learning,  K-means, Dimentionality Reduction
Coursera, Machine Learning, Unsupervised Learning,  K-means, Dimentionality Reduction
 
 
the 1st step of PCA algo is data preprocessing
Coursera, Machine Learning, Unsupervised Learning,  K-means, Dimentionality Reduction
 
 
PCA algo in matlab:
  Coursera, Machine Learning, Unsupervised Learning,  K-means, Dimentionality Reduction
Coursera, Machine Learning, Unsupervised Learning,  K-means, Dimentionality Reduction
 
How to de-compress back from 100-dimentional to 1000-dimentional
 
Coursera, Machine Learning, Unsupervised Learning,  K-means, Dimentionality Reduction
How to choose the parameter K
  Coursera, Machine Learning, Unsupervised Learning,  K-means, Dimentionality Reduction
 
 
  Coursera, Machine Learning, Unsupervised Learning,  K-means, Dimentionality Reduction
Advice for using PCA. PCA is often used for data compresion and visualization. it is bad to use it to prevent overfitting.
上一篇:jquery之toggleClass应用


下一篇:06-图2 Saving James Bond - Easy Version (25 分)