I’m implementing a model that requires using the gradients of a feedforward network with respect to its inputs as part of the loss function. I then need to train the network by differentiating the loss with respect to the parameters of the network. I can’t seem to get this working due to ERROR: Muta…

PyTorch cannot backpropagate through mutations and neither can Zygote. The expression fill!(similar(y), 1) depends on x through y and mutates its arguments (see the exclamation mark). You know that there is no real dependency on the value of y because the outcome is constant but Zygote will still tr…

Gradient of gradient

Specific Domains Machine Learning

xiaodai November 6, 2020, 2:11am 3

this is quite odd.

Topic		Replies	Views
Compute gradients in neuralODE with Zygote Machine Learning	3	280	August 24, 2023
How to use gradient of neural network as the loss function? Machine Learning question	13	2828	March 23, 2021
Flux loss: Gradient wrt input leads to empty gradient wrt parameters or to "can't differentiate foreigncall" Machine Learning flux , forwarddiff , diffeqflux	3	593	April 8, 2022
Autograd through loss function with derivatives in Machine Learning	1	904	March 25, 2021
Jacobian of NN: Mutating arrays is not supported Machine Learning	2	406	February 11, 2021

Gradient of gradient

Related topics