In this (helpful!) post, https://kiranshila.com/index.php/2020/02/04/teaching-myself-machine-learning-with-julia-part-1/ The (zygote) gradient call is g = gradient(model -> mse(model.(x),y), model) I tried instead doing g = gradient(() -> mse(model.(x),y), model) and it did not work. Wh…

[image] jaynick: Suppose the function has two arguments, h(x,y) = x+y How do you get the gradient with respect to y? gradient(y->h(x, y), y)

In Zygote, why (model)->... in gradient

Specific Domains Machine Learning

baggepinnen February 10, 2020, 6:15am 4

What you write means the following
g = gradient(z-> mse(z.(x),y), model)
You take the gradient of the anonymous function with respect to its input in the point model

Topic		Replies	Views
Help with Zygote and parameters New to Julia zygote	6	1501	July 1, 2020
Need some help in understanding zygote gradient Machine Learning	2	413	September 7, 2022
Zygote: treating a model output as a constant Machine Learning zygote	2	740	February 4, 2020
Strange behavior of differentiating constant functions in Zygote New to Julia	1	329	December 23, 2019
Differentiating implicit parameters using Zygote in complex hierarchical models New to Julia question , differentiation , flux	0	937	January 16, 2019

In Zygote, why (model)->... in gradient

Related topics