News for hackers. Stuff that matters.
Re:The Matrix Calculus You Need for Deep Learning by imh on Friday June 29, 2018 @03:57AM (#17423096)
Look up maximum likelihood estimation [0] and look up newton's method[1]. Take the log likelihood of your data and find the parameters which maximize it. If that doesn't make sense, read up on numerical optimization.

[0] https://en.wikipedia.org/wiki/Maximum_likelihood_estimation

[1] https://en.wikipedia.org/wiki/Newton%27s_method_in_optimizat...

There are no comments on this comment yet.