i cant thank you enough for this playlist you are the best >

You are so sad, you probably don't have a husband because you have been brainwashed by feminism.

Maths = Mathematics is plural. Be consistent.

Social science is pure communism. Evolutionary psychology at mankind quarterly is not.

why do we begin at y sub zero and not y sub 1?

Why say 5 year old wordds like 'cool fact' cmon, you're an adult with good explanations yet you resort to 'cool'

Head circumference does correlate with IQ at .3 because of brain size.

Im here to learn PCA too. I research IQ on my own. Thanks.

Being left handed is a sign of genetic mutation and brain maladaptation. You sound like a far left extremist.

Maths. Math is incorrect. Mathematics is plural.

Americans speak English with bad grammar. It's different to, not different than.

PCA excellently simplified. Thanks

I can't thank you enough for making this lecture series available for free here. I'm a big-picture and a visual learner and your teaching approach fits my learning style really well. Any chance you can do a lecture on, probably, intro to operations research/optimization (or some more lectures in statistics and/or machine learning) or any outside resources you would recommend on the topic that have a similar pedagogical style? Thanks again!

This video saved my life

thanks

Hyperplane need not always be 1 lesser dimension? A 2D hyperplane is also possible from a 4D ambient space right? Basically the dimension of the hyperplane has to be lesser than the dimension of the ambient space, is that right?

thanks

thanks

Really appreciate your efforts for this great explanation ❤

The "wee..." alone deserves a million likes!😂

Thank you so much, you made algebra and linear regression click for me

Excuse me I really like your work. Could you also provide solutions for the practicals as well?

Thanks a ton!🙏

I'm not sure this is what I am looking for, if it is, then I missed it. I have an implicit function f(x,y,z)=0 (it is actually a model with adjustable parameters). I have an experimental data point (Xexp, Yexp, Zexp). You can probably see where I am heading with this. I want to know where a line, orthogonal/perpendicular to the surface, will intersect the surface. I'm calling this point of intersection Xcalc, Ycalc, Zcalc. How do I proceed? Based on other videos I watched, it looks like the first step is to linearize the surface using Taylor series. So, now I have a plane (in terms of partial derivatives and (Xcalc, Ycalc, Zcalc) which is still unknown. I want to know the point of intersection (Xcalc, Ycalc, Zcalc) of the orthogonal line from Xexp, Yexp, Zexp. At first, I thought is it a trial an error iterative procedure (I have to guess Xcalc, Ycalc, Zcalc) so I programmed that, but the answers I am getting do not seem to be correct. I'm also beginning to suspect that the solution can be direct, not iterative. Any thoughts?

Thank you for doing this

Choosing the objective of the model resonates with me. That is a problem / need I face regularly during my job as a data scientist in healthcare.

This is the best intuitive explanation of eigenvalues and eigenvectors I've ever seen. And I saw a lot of them :D

That's amazing video, Beautiful explanation of linear regression in terms of linear algebra.

This is just way too good. Thanks a lot!

Great content! This was the missing link between my linear algebra and econometrics courses :D

🤘

Very amazing lecture! thank you very much for your efforts. Is the line from the origin to the point y_hat the regression line please?

how do we come up with the prototypes against each class. i understand the part where we get similarity measure between the CNN features and prototypes, but where does these prototypes comes from in the first place? As mentioned in the paper, they are also learn, but I am failing to understand that part. can you kindly explain that too in the comments

Amazing! cleared lots of confusions

Very informative.

Hello. Thank you for the explanation. Is there any rule/paper/reference which suggest how many singular values to keep or throw away for best noise reduction? Thank you.

Thank you so much for your channel

I just completed lesson 2 and am finding it much easier to follow than 3brown1blue videos. I also love the practice exercises at the end. Thank u for this.

Is this ok for those starting out in linear algebra

Is the max/min ratio plot based on draws from the a multivariate gaussian with increasing dimensions? Background: I tried to replicate this for a class of mine with a multivariate gaussian but somehow it doesn't converge as nicely as your plot. Could be a plotting issue tho. After 500 iteratios I have a ratio of 2.711633 based on eucledian distance.

Such a great explanation! Thanks a lot

Thank you 😀

Thank you for making these, really well done. Some of the best videos I've seen on linear algebra.

As the dimension increases, more space(or volume) will concentrate on the surface or corner of the total space, and most of the sample vectors will be orthogonal to each other at 10:34, Thanks for your great explanation!

the best explanation! thanks!

Great video. Could you explain more why all of the volume of the hypercube is contained in the corners as the dimensions grow?

very useful video!!!

The slides and code are publicly available here: drive.google.com/drive/folders/1skrvdCc581TN1VL3Cvx2-E4Nt0sZb8sO

Nice explanation, really well done. I have one question.: Given a real variance-covariance matrix, which of the following is true. A) it's eigenvalues can be +ve & -ve B) it is always non-singular C) it's eigenvectors are mutually orthogonal D) it's size depands both on image size & number of bands. (MSQ)