Machine Learning (ML) is already here and in your Post-Production tools, and I, for one, welcome our new robot overlords.
In this issue of Cut/daily I'll highlight five different ways Machine Learning is already super-charging your post workflows but do we have the 'enhance' button yet?
To Nerd-splain for a minute, A.I. and M.L. are quite different things.
Artificial intelligence is the science and engineering of making computers behave in ways that, until recently, we thought required human intelligence.
— Andrew Moore, Former-Dean of the School of Computer Science at Carnegie Mellon University
A.I. is mostly what you think of when you think of A.I.
Intelligent machines that can think and act upon their own objectives.
(FYI TM vs TM is hilarious)
Machine Learning, however is a branch of A.I. and far more constrained:
Machine learning is the study of computer algorithms that allow computer programs to automatically improve through experience.
— Tom M. Mitchell, Computer Scientist
Given a large enough dataset of images, of say people smiling, the computer program would be able to iteratively learn what a smile looks like based on patterns of pixels and so predictively tag photos of people smiling.
Machine Learning sits behind the following Post-Production software features and applications, although I'm sure this is just the beginning of all the 'magical things' that will soon become possible.