-
I am trying to run and understand 2.Demo_optimize_bullet_trajectory.ipynb in seminars/2019-03-Neural-Ordinary-Differential-Equations but when I arrive at the line where you want to import a few things…
-
Hello again,
I'm pretty new to neural ODEs and differential equations in general. I hope I'm not wasting your time as this may be a sort of dumb question.
I am trying to learn the functions that …
-
Hallo,
Warnmeldungen mit Beta Test vom JS Controler:
js-controller 3.2.x - has no existing object nac
`
musiccast.0 | 2021-01-11 23:19:36.318 | warn | (16672) State "musiccast.0.RX-V481_08125…
-
I have been getting "underflow in dt 0.0" after a few epochs of training. I am using Adam and lr of 1e-5(decreased from 1e-3, still not working). Any idea why this is happening? Do you have any sugges…
-
Perhaps because it's a multidimensional problem?
```
using DiffEqFlux, Flux, DifferentialEquations
z_grid = -5:0.1:5.
v̄(z) = 2*exp(z)
N = length(z_grid)
function f(du, u, p, t)
v = u…
-
For instance, let's say I have an inverted pendulum that I'd like to describe as `x_dot = x+u` and I know when and how long `u` was applied; I wish to predict the evolution of `x_t+k` given `x_t` and …
saihv updated
4 years ago
-
Hi @zekeriyasari, this is a really cool package! @chrisrackauckas pointed it to me. While I'm taking a look, it occurred to me that it perhaps should consider a different name. Specifically, the packa…
-
```julia
using DiffEqFlux, OrdinaryDiffEq, Flux, Optim, Plots
…
-
Seems to be a bug in `nt.predict.gradient_descent`, perhaps related to flattening of inputs. Code snippet and stacktrace below.
Code snippet:
```
def ntk_loss(fx,y_hat):
return -np.mean(np.s…
-
Hello,
I was wondering whether there's a more efficient way of sending additional input parameters to ODEfunc in the forward pass, than appending the additional parameter as part of the tuple-state…
ghost updated
4 years ago