News for hackers. Stuff that matters.
Re:Empiricism and the limits of gradient descent by LolWolf on Monday May 28, 2018 @01:37AM (#17170748)
In this case, any linear model (with reasonable, minimizable loss, which could be, say convex) will learn the correct thing.

Here's a quick gist[0] doing it using least-squares, and learning it exactly (also, for B in the third row you may have intended 35 instead of 45?).

This simple regression model learns exactly the weights (-1, 1)—equivalently, it learns -A + B = C.

------

[0] https://gist.github.com/guillean/6f3ff05fa99b2b377fcf309bdc4...

There are no comments on this comment yet.