News for hackers. Stuff that matters.
Re:Composability in Julia: Implementing Deep Equilibrium Mod... by gugagore on Thursday October 21, 2021 @10:47PM (#28953213)
well, I think it has to be a fixed f for the interpretation of a (time-invariant) dynamical system x_{n+1} = f(x_n) to work.
Re:Composability in Julia: Implementing Deep Equilibrium Mod... by taeric on Friday October 22, 2021 @12:16AM (#28953706)
But deeper layers of the network don't get the original input, do they?