Difference between revisions of "User talk:Joyce Whang"

From Computational Statistics (CSE383M and CS395T)
Jump to navigation Jump to search
 
Line 5: Line 5:
 
- We can reduce a complex data set to a lower dimension by PCA. <br>
 
- We can reduce a complex data set to a lower dimension by PCA. <br>
 
- PCA is defined as the orthogonal projection of the data onto a lower dimensional space in such a way that the variance of the projected data is maximized. <br>
 
- PCA is defined as the orthogonal projection of the data onto a lower dimensional space in such a way that the variance of the projected data is maximized. <br>
 +
- Intuition: given high-dimensional data, some attributes are redundant. We can compress the data without much loss of information by PCA.

Latest revision as of 03:46, 9 April 2012

In this term project, I will make a lecture about Principal Component Analysis (PCA). PCA is one of the most widely used techniques for linear dimensionality reduction.

1. Motivation
- PCA is introduced to deal with the problem of excessive dimensionality.
- We can reduce a complex data set to a lower dimension by PCA.
- PCA is defined as the orthogonal projection of the data onto a lower dimensional space in such a way that the variance of the projected data is maximized.
- Intuition: given high-dimensional data, some attributes are redundant. We can compress the data without much loss of information by PCA.