If someone likes more lecture style explanation I can recommend 3blue1brown's material on YouTube. He explained in a pretty good an accessible way imho.
I didn't learn artificial neural network stuff from there. I knew those concepts but I didn't know the matrix formalism applied to it. So this was really nice to understand why GPUs are good for this. Math-wise it was really nice watch.
No. It can check whether the operands will cause overflow and issue an error instead of silently giving a bogus result.
It's a performance hit though.
I don't think you'd want a banking app written with assumption that you'll never have more than MAXINT amount of dollars, and adding few more will roll you back to 0 or even put you in debt... silently... because well it works this way, and designer didint think you'll hit the limit. If it ever happened you'd like a siren to go off.
The problem is that UB is invoked on runtime for particular inputs... And it silently makes program unreasonable after this point.
That is not good. It's hard to reason about such a program, in other words can you trust results of such a program? How do you know whether your input caused Ub at some point or not?
The burden of sanitizing the input is on the user (either programmer or the data provider).
Checking this is usually a performance tradeoff, so it was decided not to be done by default.
The article is tautological. It basically says that only some people get blackouts because they tolerate alcohol differently. It's like saying only some people blackout because only some drink.
I thought some people can't experience it. It seems they just didn't get drunk enough.
We got good models for pretty good chunk of phenomena of scales from subatomic to galaxy wide and beyond. Astonishing is the fact that same laws give good predictions on both ends of the scale. I think that's the reason behind the assumption we have most figured out.
But in the middle happens most what we cannot comprehend. How does a cell know when to divide. How exactly the process goes. Why do we have consciousness? Having theories capable of describing atoms and stars we can't figure out the middle, this is fascinating.
Imho the issue is the complexity of system. Stars and atoms are actually not that far apart. In the middle the amount of effects with comparable magnitude and stable states are the greatest.
Why the distaste? I treat it as a study of phenomena. It's like a social study on rather grand scale. It doesn't different species much from the crowd dynamics, useful in better design of evacuation routes.
The application is not life-saving, but the conclusions are the same. It's like dynamite and atom splitting. You can use it for the good and for the bad.
> it's important to understand what's going on in these companies.
This is simple. They study people's behavior to drive it for their benefit. The basics of it should be taught in high school, so people better understand themselves.
To my knowledge they explore solution space but not through a gradient descent but by probing.
How can you perform a GD on non continuous function? Genetic algorithms and evolutionary methods can explore disjoint domains and functions hard from analytical pov.
Just because they can be used for gradient descend doesn't mean they use it.
Ok imagine you are seeing a screen and from behind you is coming a photon. How do you know whether there was a double slit behind you or not for a single photon?
Those are two situations that will lead to the same outcome and you don't know which happened.
Also reverse is possible. You have the same situation evolving into two different situations with double slit and interference.
How does granular analysis differ from pcm representation, Fournier transformation and sampling? Or is it a different name for the same thing. I think it's natural to whoever worked with sound on a Pc.
It's probably debatable, but I don't agree with the statement that shortnening the "sound" changes pitch. It depends on your representation of the sound. If you represent it as a function of amplitude vs time then scaling the time axis does change pitch.
This makes a sensational tone about a fallacy. No instrument plays sound faster or slower to make it shorter or longer.... It just stops playing it or doesn't. If one thinks about the phenomenon this way, it becomes natural why you cannot compress time, to play shorter sounds.