PCA 6: coordinates in low-dimensional space

Full lecture: bit.ly/PCA-alg
We can project our data to the new low-dimensional space by doing an inner product of each instance with each of the principal components (eigenvectors). The resulting number is the coordinate of that instance along the corresponding dimension. Don't forget to subtract the mean (center the data).

[@soharostaminia4536]

The best PCA tutorial series ever!

[@rockspeed2010]

Thank you for the videos.. really informative and the best explanation for PCA so far on the net.

[@snowdrop79]

Thank you for the videos! I think the x' in 1. "center" ... and 2. "project" ... parts should actually be x (original coordinates), right?

[@anranwang389]

Thank you for your great video.
Is the slide file available online? Thank you!

[@saunakroychowdhury5990]

but is not projection (y .e)e where y = x - mew