31–40 of 251 posts
I also have some notebooks with SymPy code examples here: https://github.com/minireference/noBSLAnotebooks
Somewhat surprising there is no mention of basic design principles, or understanding the quirks of human perception. My brother was a production artist for some well-known computer games in the '90s-'00s, and continually complained about programmers and managers with zero visual sense, or curiosity about understanding the artists' side. Graphics aren't my specialty, but as a musician, sound designer and producer, by…
Earlier quoted context omitted.
Graphics programming has this one very, very useful aspect, exponentially more valuable today: the matrix algebra pipelines, and then the requirement to 'think in matrix transforms' is a wonderful and visually engaging way to get your foundation for machine learning math.
This is like saying being a cashier prepares you for a job in high-finance because both involve arithmetic on dollars and cents. I've been in ML for ~5 years in multiple FAANGs and I have never seen a rotation matrix .
Earlier quoted context omitted.
This is like saying being a cashier prepares you for a job in high-finance because both involve arithmetic on dollars and cents. I've been in ML for ~5 years in multiple FAANGs and I have never seen a rotation matrix .
Is the linear algebra of machine learning more complicated than that of graphics?
Today, I would not recommend anybody to go into graphics programming: I started in 2001, when NVidias first Geforce 1 ("the Gigatexl shadercard") was first announced: The field developed since then with so much speed and innovations, it blows my mind of. Compared to what we could do 25years ago, the tech today is just fu*ing impressive. Though, with this impressiveness comes a big "but": The space is developing at a…
Graphics programming has this one very, very useful aspect, exponentially more valuable today: the matrix algebra pipelines, and then the requirement to 'think in matrix transforms' is a wonderful and visually engaging way to get your foundation for machine learning math.
The trick there is that they both have related physical analogs, and machine learning math doesn't really (in that while you can visualize them spatially, it doesn't seem to help solve any problems in that space.)
Earlier quoted context omitted.
This is like saying being a cashier prepares you for a job in high-finance because both involve arithmetic on dollars and cents. I've been in ML for ~5 years in multiple FAANGs and I have never seen a rotation matrix .
Doesn’t RoPE use 2D rotation matrices ?
If anyone needs a quick tutorial on linear algebra, you can check out this printabale four pager that I wrote: https://minireference.com/static/tutorials/linear_algebra_in... I also have some notebooks with SymPy code examples here: https://github.com/minireference/noBSLAnotebooks
I'm a graphics programmer. The most useful resources I've found for graphics are scratchapixel, UC Davis' graphics lectures, songho's articles, and Essential Math for Games and Interactive Applications. I highly recommend you read this last resource front to back. Seriously, its the best freaking math reference for graphics out there. But knowing theory is not sufficient. You also need to get your hands dirty by writ…
I will definitely check out Essential Math for Games and Interactive Applications, I feel I need some solid understanding of theory to see how it all fits together.
Earlier quoted context omitted.
This is like saying being a cashier prepares you for a job in high-finance because both involve arithmetic on dollars and cents. I've been in ML for ~5 years in multiple FAANGs and I have never seen a rotation matrix .
Is the linear algebra of machine learning more complicated than that of graphics?
Today, I would not recommend anybody to go into graphics programming: I started in 2001, when NVidias first Geforce 1 ("the Gigatexl shadercard") was first announced: The field developed since then with so much speed and innovations, it blows my mind of. Compared to what we could do 25years ago, the tech today is just fu*ing impressive. Though, with this impressiveness comes a big "but": The space is developing at a…