I have recently started using Flux to construct a physics informed neural network. To do this, I start with a model u = Chain(Dense(1, 10), Dense(10,15), Dense(15,1)) Then I construct a function to impose the differential condition y’(t) - y(t) = 0 function f(t) y = sum(u(t)) dy = gradient(() …

Using Flux for a neural net solution to differential equations

ChrisRackauckas June 25, 2020, 2:55am 4

Look at NeuralNetDiffEq.jl which is a repo of physics-informed neural network implementations and deep BSDE methods.

1 Like

Gradient error in Flux model inputs

Topic		Replies	Views
Flux differentiation error Machine Learning zygote	19	1669	November 19, 2020
Flux + Automatic Differentiation Machine Learning	3	532	January 19, 2023
Flux loss: Gradient wrt input leads to empty gradient wrt parameters or to "can't differentiate foreigncall" Machine Learning flux , forwarddiff , diffeqflux	3	530	April 8, 2022
Gradient error in Flux model inputs Machine Learning question , flux , zygote	5	1302	January 13, 2021
"Can't differentiate foreigncall expression" error while using Flux.train! General Usage question , diffeq , flux , zygote	1	632	February 13, 2022