News for hackers. Stuff that matters.
Re:Extreme Video Compression by Rygian on Tuesday February 20, 2024 @04:58AM (#39439509)
How does that make sense? Compression is deterministic (for same prompt, same output is algorithmically guaranteed). AI is only deterministic in corner cases.
Re:Extreme Video Compression by leoff on Tuesday February 20, 2024 @05:05AM (#39439551)
AI is always deterministic. We add noise to the models to get "non-deterministic" results, but if the noise and input is the same, the output is also the same.
Re:Extreme Video Compression by david-gpu on Tuesday February 20, 2024 @09:42AM (#39441872)
It's a bit more nuanced than that. Floating point arithmetic is not associative: "(A+B)+C" is not always equal to "A+(B+C)". Because of that, certain mathematical operations used in neural networks, such as parallel reductions, will yield slightly different results if you run them multiple times with the same arguments.

There are some people working hard to provide the means to perform deterministic AI computations like these, but that will come with some performance losses, so I would guess that most AIs will continue to be (slightly) non-deterministic.

Re:Extreme Video Compression by nuancebydefault on Tuesday February 20, 2024 @03:53PM (#39446757)
Is AI in general relying on floating point calculations?
Re:Extreme Video Compression by david-gpu on Wednesday February 21, 2024 @03:30AM (#39451394)
One hundred percent. It's mostly fancy floating point matrix multiplications.
Re:Extreme Video Compression by Rygian on Wednesday February 21, 2024 @07:11AM (#39452854)
That assumes an AI that is trained exactly once ever.