Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Matrix Calculus for Deep Learning

parrt.cs.usfca.edu

Post reply on HN
Print view View original

71–80 of 84 posts

Re: Matrix Calculus for Deep Learning

#71

Post by parrt »

dbetteridge wrote: post #65
parrt wrote: post #12

Earlier quoted context omitted.

I agree that the font should be bigger. I need to learn more CSS in order to switch between font sizes per platform. The font of the text is easy but all of the images were generated from latex using a specific font size. I need to scale the in-line equation images as the font size bumps up.

the magic incantation here is probably media queries @media (max-width: 768px) { p { font-size: 1rem; } }

We have to also adjust the image sizes for the in-line equations. That’s what I need to figure out :)

Re: Matrix Calculus for Deep Learning

#73

Post by Dawny33 »

jtmcmc wrote: post #13
jph00 wrote: post #4

Jeremy here. Here to answer any questions or comments that you have. But more importantly - I need to mention that Terence Parr did nearly all the work on this. He shared my passion for making something that anyone could read on any device to such an extent that he ended up creating a new tool for generating fast, mobile-friendly math-heavy texts: https://github.com/parrt/bookish . (We tried Katex, Mathjax, and prett…

This is great! my graduate advisor a long time ago made a really great matrix calculus study sheet for me that was absolutely invaluable in learning ML ( i mean really this is great for not just DL but all sorts of reasoning in ML)

Wondering if you still have that with you? Would be super useful for folks here.

Re: Matrix Calculus for Deep Learning

#74

Post by letlambda »

>For functions of a single parameter, /partial operator/ is equivalent to /full derivative operator/ (for sufficiently smooth functions).

Are you pulling my leg here, or do I need to scrap my understanding of calculus?

If they exist, how could they not be equivalent?

Re: Matrix Calculus for Deep Learning

#75

Post by tmbsundar »

lprd wrote: post #22

In school, I didn't make it much past basic calculus/algebra. As a self-taught programmer (my highest level of education is a high-school diploma), I seriously wish I could go back and put more effort into math. I love looking at these types of topics, but I have absolutely no clue what I'm looking at. If anyone can recommend any books, courses, or any other material that starts from high-school level math, and gradu…

Try "Methods of Mathematics Applied to Calculus, Probability, and Statistics" by Richard Hamming

Re: Matrix Calculus for Deep Learning

#76

Post by TheArcane »

jph00 wrote: post #4

Jeremy here. Here to answer any questions or comments that you have. But more importantly - I need to mention that Terence Parr did nearly all the work on this. He shared my passion for making something that anyone could read on any device to such an extent that he ended up creating a new tool for generating fast, mobile-friendly math-heavy texts: https://github.com/parrt/bookish . (We tried Katex, Mathjax, and prett…

There are discrepancies between the HTML and pdf version.

Eg. In the first line in 'References'

HTML: "When looking for resources on the web, search for “matrix calculus” not “vector calculus.” "

Latex/pdf: "When looking for resources on the web, search for “elements” not “elements” "

Re: Matrix Calculus for Deep Learning

#78

Post by parrt »

TheArcane wrote: post #76
jph00 wrote: post #4

Jeremy here. Here to answer any questions or comments that you have. But more importantly - I need to mention that Terence Parr did nearly all the work on this. He shared my passion for making something that anyone could read on any device to such an extent that he ended up creating a new tool for generating fast, mobile-friendly math-heavy texts: https://github.com/parrt/bookish . (We tried Katex, Mathjax, and prett…

There are discrepancies between the HTML and pdf version. Eg. In the first line in 'References' HTML: "When looking for resources on the web, search for “matrix calculus” not “vector calculus.” " Latex/pdf: "When looking for resources on the web, search for “elements” not “elements” "

Whoops. thanks. translator error. I'll fix it.

Re: Matrix Calculus for Deep Learning

#79

Post by MarkMMullin »

parrt wrote: post #7
jph00 wrote: post #4

Jeremy here. Here to answer any questions or comments that you have. But more importantly - I need to mention that Terence Parr did nearly all the work on this. He shared my passion for making something that anyone could read on any device to such an extent that he ended up creating a new tool for generating fast, mobile-friendly math-heavy texts: https://github.com/parrt/bookish . (We tried Katex, Mathjax, and prett…

Terence here. Jeremy's role was critical in terms of direction and content for the article. Who better than he to describe the math needs for deep learning. :)

Glad to see you in this space Terrance! Been a long time since the traveling parser revival and beer tasting festival!

Re: Matrix Calculus for Deep Learning

#80

Post by parrt »

claar wrote: post #52
improbable22 wrote: post #51

Earlier quoted context omitted.

Like this, perhaps? A = {{1,2},{3,4}} vec = {x^2, x^3} D[vec.A.vec, x] Or perhaps like this, again the table of derivatives: xvec = {x1,x2} Table[ D[xvec.A.xvec,x] ,{x,xvec}] (all untested... one typo caught...)

http://www.wolframalpha.com/input/?i=D%5B%7Bx%5E2,+x%5E3%7D....

Added Link to Wolfram Alpha...
Post reply on HN