I am trying to use ForwardDiff to check some analytic gradients for a mse loss and logistic hypothesis function. So just looking at the loss of a single data point we have mse(x) = (1/2)*((y - logistic.(transpose(x)*w))^2) Where x and w are dimensionally consistent arrays. When using ForwardDiff…

ForwardDiff with function using broadcasting

Tamas_Papp October 25, 2020, 8:41am 2

Please provide an MWE.

Topic		Replies	Views
Gradients of a simple function using ForwardDiff yields errorenous results? - Or am I doing something wrong? New to Julia package	2	359	November 12, 2020
Problem with ForardDiff New to Julia package , forwarddiff	1	253	June 8, 2022
Types and gradients, including Forward.gradient General Usage	20	5529	December 20, 2016
Issues with computing gradient with ForwardDiff.jl (Any fixes other than ND?) Machine Learning forwarddiff , neural-network	2	213	December 24, 2023
ForwardDiff failing on simple polynomial New to Julia	1	941	September 28, 2017