Summary of all notes: summary of reading notes for statistical learning methods
Free PDF download: "Statistical Learning Methods (Second Edition)"
Principal component analysis (PCA) is a commonly used unsupervised learning method. This method uses orthogonal transformation to convert the observation data represented by linear dependent variables into a few data represented by linear independent variables. Irrelevant variables are called principal components.
1. Overall principal component analysis
There may be correlations between the variables of the data, which increases the difficulty of analysis. Consider replacing related variables with a few irrelevant variables to represent data, and it is required to retain most of the information in the data.
The main purpose of principal component analysis is to reduce dimensionality, so generally choose k (k <<m) k (k <<m)k(k<<m ) principal components (linear independent variables) instead ofmmThe m original variables (linearly dependent variables) simplify the problem and retain most of the information of the original variables.
2. Sample principal component analysis
Can be compared to Example 16.1.
Next Chapter Portal: Reading Notes on Statistical Learning Methods (17)-Latent Semantic Analysis