I’m trying to use the DiffEqFlux package to define a machine learning model for a differential equation. The model I want needs to work similar to a Nueral ODE, but with latent variables. So I have the following: \frac{dh}{dt} = F(h_{t-1}, x_t) Thus when writing my model, I need to make the diffe…

[image] mllera14: What would this look like? Sorry this is my inexperience with Julia talking. I guess my expectation was something like a recurrent network, which in traditional ML frameworks take an input X , which in this case is I(t) and the hidden state h0 . I(t) = t^2 function f(du,u,p…

Defining and input signal for a differential equation

New to Julia

ayaoyao214 November 25, 2020, 2:45am 19

Sure, I got this. Then its more likely to be the other part of my model went wrong or my feature set is not suitable. Thanks for comfirming this for me !!

Topic		Replies	Views
DiffEqFlux with time as additional input to Neural ODE Machine Learning first-steps	7	2260	July 21, 2019
Provide parameters and user-defined functions to neural_ode in DiffEqFlux.jl General Usage diffeq , flux	1	431	February 25, 2019
DifferentialEquations & inputs General Usage	2	381	June 11, 2019
DifferentialEquations.jl + Flux.jl or Knet.jl Machine Learning diffeq	15	3648	October 18, 2018
DiffEqFlux.jl – A Julia Library for Neural Differential Equations Machine Learning diffeq	1	1069	January 24, 2019

Defining and input signal for a differential equation

Related topics