Introduction Principal Components Analysis (PCA) is a dimensionality reduction algorithm that can be used to significantly speed up your unsupervised feature learning algorithm. More importantly, understanding PCA will enable us to later implement whitening, which is an important pre-processing step for many algorithms. Suppose you are training your algorithm on images. Then the input will be some
![Unsupervised Feature Learning and Deep Learning Tutorial](https://cdn-ak-scissors.b.st-hatena.com/image/square/b460888899cdd328b8c63f248846d3f366f551bd/height=288;version=1;width=512/http%3A%2F%2Fufldl.stanford.edu%2Ftutorial%2Fimages%2FPCA-rawdata.png)