Good question! This is legitimate because by finding our optimal D(x), we are directly maximizing the integrand at every point x. Since our integrand can never be higher for any other D(x) at a specific point x; then if we find this maximum for every x, then we are guaranteed to maximize the integral as a whole.
Always expect the earliest video from your channel
I am about to do oral exam for my phd . my main project involves the deployment of GANS and VAEs ,,your videos are amazing
Well done! Very thoroughly explained.
what if my D(x) is 0.52-0.54 for increasing epochs, but the discriminator losses are higher than generator losses, does this mean convergence?
One question. Why max{ \int_x {f(x) dx} } is the same thing as max{ f(x) }?
Good question! This is legitimate because by finding our optimal D(x), we are directly maximizing the integrand at every point x. Since our integrand can never be higher for any other D(x) at a specific point x; then if we find this maximum for every x, then we are guaranteed to maximize the integral as a whole.
Well, i can’t miss your video
Chad
My brother, please, can you create a course to learn the manim library for beginners? ☺️🤍🤍
I'm not too familiar with it, but 3Blue1Brown has a tutorial!