SVD: Eigenfaces 1 [Matlab]

This video describes how the singular value decomposition (SVD) can be used to efficiently represent human faces, in the so-called "eigenfaces" (Matlab code, part 1).

These lectures follow Chapter 1 from: "Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control" by Brunton and Kutz

This video was produced at the University of Washington

[LusidDreaming]

These videos + the book are absolutely incredible! Thank you so much for putting all this together so engineering students like myself can learn the fundamentals of data science (and also be reminded of how much linear algebra we forgot).

[jeffrogers]

You are an amazing instructor, Steve. I have a project for our education platform, being used in Japan, Vietnam and India right now. Do you have any interest in consulting?
Thanks

[machaitem]

If I have another dataset, how to create .mat file that store all the variables like allFaces.mat?

[merveozdas]

You didn't define m and n, how does program recognize it and how did you read images, I could not understand, can you help me?

[jd-ntoc]

Hum... why there is only 2410 columns, as 38 persons with 64 lighting conditions gives 2432 images. It is as if 22 images of some lighting conditions were missing. Will it affect the quality of the decomposition?

[guhanmuthu]

what does nfaces data matrix siginify ?

[dikshyasurvi]

I cannot get the dataset anywhere. The link given doesn't work.

[yaraali]

Hi..
How to rotate pca's in matlab?

[humayunkabir-lblm]

fscial recognition using svd plz code math lab