A lot of students come up to me and ask about when they’re going to learn the latest and greatest new deep learning algorithm.
Sometimes, it’s easy to forget how applicable even the most basic of tools are.
As you know, I consider Linear Regression to be the best starting point for deep learning and machine learning in general.
And wouldn’t you know, here it is being used in the most advanced, state-of-the-art video codec we have today:
next generation video: Introducing AV1
Check it out!
This new state-of-the-art video codec is based on research done by multiple big companies, such as Google, Cisco, and Mozilla.
As you can see, the final equation is just a line (\( y = mx + b \)).
$$ CfL(\alpha) = \alpha L^{AC} + DC $$