This tag is intended for questions about or involving the usage of Flux: an open-source machine-learning library written in Julia. Flux takes full advantage of Julia's just-ahead-of-time compilation and exposes an intuitive and flexible interface to users, while still providing a layer-stacking-based interface for simpler models, and can be readily integrated with other Julia packages.
Questions tagged [flux-machine-learning]
19 questions
1
vote
1 answer
Updating parameters of a function with Flux.jl
I'm playing around with flux.jl and I'm having trouble updating the parameters of a custom function.
The function is defined below as objective:
using Distributions
using Flux.Tracker: gradient, param, Params
using Flux.Optimise:…
vtrubets
- 341
- 1
- 9
0
votes
1 answer
Ways to Improve Universal Differential Equation Training with sciml_train
About a month ago I asked a question about strategies for better convergence when training a neural differential equation. I've since gotten that example to work using the advice I was given, but when I applied what the same advice to a more…
0
votes
1 answer
How to guarantee convergence when training a neural differential equation?
I'm currently working through the SciML tutorials workshop exercises for the Julia language (https://tutorials.sciml.ai/html/exercises/01-workshop_exercises.html). Specifically, I'm stuck on exercise 6 part 3, which involves training a neural…
0
votes
1 answer
Julia ERROR: UndefVarError: σ not defined
I am running this from julia:
W1 = param(rand(3, 5))
b1 = param(rand(3))
layer1(x) = W1 * x .+ b1
W2 = param(rand(2, 3))
b2 = param(rand(2))
layer2(x) = W2 * x .+ b2
model(x) = layer2(σ.(layer1(x)))
model(rand(5))
I am getting this error:
ERROR:…
Krishna Wadhwani
- 50
- 8