AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
The Origin of the Back Prop Idea
Backprop is kind of a statisticians nightmare. You have you twiddling all these parameters and you're not really being able to do it. There's no there's no real theory behind it. It's just taking gradients. But it works very well. You could argue it's the it's the great savior of multivariate calculus. Oh, no, no, I would we use back prop for it was this when that came in actually that saved our net talk because both the machine was taking too long. As soon as we put back prop in boy with solvent overnight.