aes

https://open.spotify.com/episode/3umFrR0Bpu1fmXpO1PzDdh?si=NPMlzRCtTZGakiuikO8GEw

This. So much this.

I’m a member of Sveriges Ingenjörer. Fortunately, I’ve never needed serious union help, but it’s probably because the background threat is more than enough. And the salary statistics alone are worth the dues!

Axioms are not like the others, they’re assumed to be true even before considering any evidence or even arguments.

Sounds reasonable, but a lot of recent advances come from being able to let the machine train against itself, or a twin / opponent without human involvement.

As an example of just running the thing itself, consider a neural network given the objective of re-creating its input with a narrow layer in the middle. This forces a narrower description (eg age/sex/race/facing left or right/whatever) of the feature space.

Another is GAN, where you run fake vs spot-the-fake until it gets good.