Can anybody explain what is meant by „gradient“ in this context? Is this a way of speeding up the search for a desirable improvement of a pixel (or cluster) in each pass?
The change in the y-axis with respect to the x-axis.
d/dx
The physics principle of diffusion inspired modern AI art
11–20 of 20 posts
Re: The physics principle of diffusion inspired modern AI art
#12Earlier quoted context omitted.
Maybe an ad for Dall-e, since Stable Diffusion has taken the art world by storm by leaps and bounds. This is made even more prominent by the lack of any mention of the competitors.
> The key insight that makes DALL·E 2’s images possible — as well as those of its competitors Stable Diffusion and Imagen — comes from the world of physics.
Missed that, thanks
Re: The physics principle of diffusion inspired modern AI art
#13Earlier quoted context omitted.
>Do engineers not take calculus anymore these days? Yes, we do, like a decade ago at school when we were forced to learn it. Then the knowledge atrophies unless you're actively using it in real life. The majority of engineers I know, including myself, work on some form of web services, mobile apps or FOTM UI frameworks, and you don't need calculus to style a progress bar or query a database
The rate of change of that progress bar would be the gradient of the progress with respect to time. Could be a handy thing to have if, for example, you were designing some progress animation...
To further your point, most UIs now don’t even go to the trouble of showing progress. It’s either an infinitely spinning glyph or a “progress” bar that just keeps scanning from left to right effectively providing zero information. Fun times.
Re: The physics principle of diffusion inspired modern AI art
#14Earlier quoted context omitted.
>Do engineers not take calculus anymore these days? Yes, we do, like a decade ago at school when we were forced to learn it. Then the knowledge atrophies unless you're actively using it in real life. The majority of engineers I know, including myself, work on some form of web services, mobile apps or FOTM UI frameworks, and you don't need calculus to style a progress bar or query a database
The rate of change of that progress bar would be the gradient of the progress with respect to time. Could be a handy thing to have if, for example, you were designing some progress animation...
Progress bars are subtly evil, they seem simple on the surface but if you want to smoothly animate them you have to know or predict the exact time each segment will take proportionate to every other segment, and in most scenarios this is an exercise in futility, so a lot of progress bars end up being fake.
I've seen a lot of cases where progress bars actually jump backwards because these predictions fail, whether it be games or applications, which feels like the universe is making fun of your existence when it happens.
Sometimes it feels like a 'this action is not stuck' indicator would be more appropriate.
Re: The physics principle of diffusion inspired modern AI art
#15Earlier quoted context omitted.
I think they refer to Gradient Descent: https://en.wikipedia.org/wiki/Gradient_descent
Do engineers not take calculus anymore these days? Gradient descent uses the gradient , but is itself not the gradient. The gradient itself is just the vector of partial derivatives with respect to each parameter. Gradient descent is just following the gradient "downwards" towards a minima. The article even describes it pretty well in non-mathematical terms. > the gradient of the distribution (think of it as the slop…
My colleague (an engineer) always looked down on peers that could not describe Gradient Descent
Re: The physics principle of diffusion inspired modern AI art
#16Can anybody explain what is meant by „gradient“ in this context? Is this a way of speeding up the search for a desirable improvement of a pixel (or cluster) in each pass?
The change in the y-axis with respect to the x-axis. d/dx
Are we not talking about a million dimensions here instead of 2? What’s x, what’s y?
Re: The physics principle of diffusion inspired modern AI art
#17Earlier quoted context omitted.
>Do engineers not take calculus anymore these days? Yes, we do, like a decade ago at school when we were forced to learn it. Then the knowledge atrophies unless you're actively using it in real life. The majority of engineers I know, including myself, work on some form of web services, mobile apps or FOTM UI frameworks, and you don't need calculus to style a progress bar or query a database
The rate of change of that progress bar would be the gradient of the progress with respect to time. Could be a handy thing to have if, for example, you were designing some progress animation...
You're trying too hard to make up fake reasons to use calculus.
Any self-respecting CS theorist would tell you that accurate progress bars are generally impossible to make because that would reduce to some version of the halting problem; and any self-respecting software engineer would tell you that even in the simple cases where the halting problem is not a problem (eg. simple copying of files), in practice many things outside of the software's control could stall the progress.
Even if you could get an accurate progress value, you don't need a "gradient" to animate it. Just update the bar with the current value as a percentage at 60FPS and you're already done. (Progress bars generally ask the programmer to supply the current progress value, not a stream of progress rates in real time) If you tried to predict the progress "gradient" past the present point, you'd end up having to "lie" (more progress than actual) or have the progress bar jump back when it turns out the actual progress was slower than predicted.
If all you had was a hammer, everything looks like a nail. That almost always applies for those enamored with advanced maths.
Re: The physics principle of diffusion inspired modern AI art
#18Earlier quoted context omitted.
The rate of change of that progress bar would be the gradient of the progress with respect to time. Could be a handy thing to have if, for example, you were designing some progress animation...
To further your point, most UIs now don’t even go to the trouble of showing progress. It’s either an infinitely spinning glyph or a “progress” bar that just keeps scanning from left to right effectively providing zero information. Fun times.
What's the point? The downfall of progress bars because software engineers don't bother to learn calculus, or that they realized trying to solve the halting problem is an exercise in futility?
Re: The physics principle of diffusion inspired modern AI art
#19Can anybody explain what is meant by „gradient“ in this context? Is this a way of speeding up the search for a desirable improvement of a pixel (or cluster) in each pass?
In this context, it refers to the gradient of the error function (which is a function of the parameters).
In other words, for each tuple of parameters you can estimate the direction in which the reduction in the resulting error would be steepest.
Gradient descent is then a method whereby you iteratively move towards better and better parameterisations, by following the direction of the (negative) gradient at each step, which guarantees you will reach a local minimum much more efficiently than if you sampled new parameters in the area of the previous iteration at random.
And if your error function is convex, the minimum error is a global minimum.
Re: The physics principle of diffusion inspired modern AI art
#20Earlier quoted context omitted.
I think they refer to Gradient Descent: https://en.wikipedia.org/wiki/Gradient_descent
Do engineers not take calculus anymore these days? Gradient descent uses the gradient , but is itself not the gradient. The gradient itself is just the vector of partial derivatives with respect to each parameter. Gradient descent is just following the gradient "downwards" towards a minima. The article even describes it pretty well in non-mathematical terms. > the gradient of the distribution (think of it as the slop…
[dead]