I’m having a hard time figuring out why this works: using Zygote W, b = rand(2, 3), rand(2) predict(x) = W*x .+ b g = gradient(() -> sum(predict([1,2,3])), Params([W, b])) g[W], g[b] but this doesn’t: using Zygote a = 2 x = 2 f(x) = x^a gp = gradient(() -> f(x), Params(a)) gp[a] I get the error: …

Help with Zygote and parameters

ettersi July 1, 2020, 8:42am 5

gradient((a1,a2)->F(L1,L2; a1=a1,a2=a2), a1,a2)

should do the trick, no?

Topic		Replies	Views
Differentiating implicit parameters using Zygote in complex hierarchical models New to Julia question , differentiation , flux	0	946	January 16, 2019
Gradient of parameters that apply only to subsets of data Machine Learning	3	752	November 18, 2019
Why calculating gradients from Params is different than doing it directly? General Usage flux	5	751	April 28, 2020
Flux/Zygote: Gradient with respect to inputs and implicit parameters (in 2021) Machine Learning question , flux , zygote	1	986	November 23, 2021
Zygote.gradient(): Mutating arrays is not supported General Usage	1	800	August 18, 2020