-
Here's a chunk of code that one could add to the UDE tutorial.
This code illustrates four things.
1. Minibatches in the loss function
2. Dynamic Composition of layers to form a model inside the…
cems2 updated
12 months ago
-
When I run this code:
```julia
using OrdinaryDiffEq, DiffEqFlux
using Optimization, OptimizationOptimisers, OptimizationOptimJL
using ComponentArrays, Lux, Plots, Random, StatsBase
using Delimite…
-
Hello！
I modeled multiple datasets using the decoupled neurodynamic model presented in the paper 'Physics-constrained Deep Learning of Multi-zone Building Thermal Dynamics'. After analyzing the eigen…
-
Hi, I'm trying to run a NeuralODE with a custom layer, `LuxNeurLayer`, I've defined in Lux. I'm receiving a MethodError when I run `prob_neuralode(u0, p, st)`. The error is:
```
MethodError: no meth…
-
Hi,
I am starting my journey in ML and Julia. I do not know if this is the correct place to ask question related to `LUX` so please forgive me.
I would like to implement a custom layer to use i…
-
Firstly, thank you for creating and maintaining this incredibly useful work.
I am trying to use equinox alongside diffrax and optax for neural network (optimal) control.
To do this I have a series…
-
Hello and thanks for this super interesting work!
I'm curious to try this with custom, image-like data, and just wondering what steps are required to get something going.
Any guidance would be aw…
-
This snippet consistently segfaults julia:
```julia
using GalacticOptim, ForwardDiff, Ipopt
rosenbrock(x, p) = (p[1] - x[1])^2 + p[2] * (x[2] - x[1]^2)^2
x0 = zeros(2)
_p = [1.0, 100.0]
f = Op…
-
Hello developers,
I am new to `Julia`, `UODE` and `sciML`.
So I have a few basic questions which I would like to clarity:
1. Where can I ask question related to `sciML`? Is the `Issues` sect…
-
Dear @ChrisRackauckas and @frankschae,
this is strongly related to issue #564 but I can narrow the error down now, see the following MWE which basically trains a minimal NeuralODE and is using a Fu…