About the Machine Learning category
|
|
4
|
2730
|
May 2, 2021
|
Has anyone tried implementing the LiMuon Optimizer?
|
|
0
|
66
|
September 29, 2025
|
What lessons could Julia's autodiff ecosystem learn from Stan's TinyGrad?
|
|
45
|
4525
|
September 26, 2025
|
Reactant.jl compile times and memory usage
|
|
9
|
153
|
September 25, 2025
|
How to ignore minibatches with NaN gradients optimizing a hybrid LUX model using Optimization.jl
|
|
0
|
38
|
September 24, 2025
|
What is the correct way to autodiff a simple CUDA kernel using Reactant.jl and Enzyme.jl
|
|
20
|
224
|
September 23, 2025
|
SciMLSensitivity fails on GPU?
|
|
5
|
52
|
September 22, 2025
|
Make Lux.jl/Zygote.jl choose gradient type based on the superset of the weight type
|
|
0
|
38
|
September 17, 2025
|
`apply` do not work anymore with StatefulLuxLayer (by Luxv1.19)
|
|
5
|
117
|
September 16, 2025
|
NamedTuple from the ComponentArray
|
|
3
|
143
|
September 11, 2025
|
Speeding up per-sample gradients?
|
|
20
|
1252
|
August 21, 2025
|
Sequence language models in Julia
|
|
6
|
353
|
August 18, 2025
|
I heard lux.jl is moving to reactant.jl. Where can I help?
|
|
4
|
288
|
August 15, 2025
|
Is it possible to evaluate the objective function within the "Optimisers.apply!" function?
|
|
2
|
60
|
August 6, 2025
|
Loading Lux params and states in a new script
|
|
1
|
66
|
August 5, 2025
|
How to use Lux.apply for a composite model
|
|
1
|
65
|
August 5, 2025
|
Using Enzyme.jl with Flux: Issues Computing Gradients of a Model with Duplicated Parameters and Mixed Forward/Reverse AD
|
|
11
|
235
|
July 29, 2025
|
Just-in-time gradient optimization idea
|
|
2
|
185
|
July 29, 2025
|
Accepted mask type for Augmentor.jl
|
|
0
|
37
|
July 28, 2025
|
Enzyme throws `alwaysinline mustprogress` when using GraphNeuralNetworks to mutate Graphs
|
|
6
|
125
|
July 15, 2025
|
NeuralPDE on GPU throws NaNs when I use a source term elevated to some power
|
|
2
|
210
|
July 6, 2025
|
How to use Lux's `apply` function?
|
|
2
|
81
|
June 30, 2025
|
Custom differentiation with Flux
|
|
2
|
61
|
June 26, 2025
|
Training Neural ODEs - Advice
|
|
2
|
110
|
June 24, 2025
|
A custom type-stable regularization function in Lux & Enzyme
|
|
0
|
77
|
June 18, 2025
|
Loading resampled data for PINN in Reactant + Enzyme + Lux
|
|
2
|
121
|
June 17, 2025
|
Issue with backprop in a custom recurrent `Lux` layer
|
|
6
|
148
|
June 16, 2025
|
Weird behavior of GraphNeuralNetworks.jl `SGConv` layer within `Flux.withgradient`
|
|
5
|
150
|
June 14, 2025
|
Native Julia FID (Fréchet Inception Distance) Computation
|
|
0
|
77
|
June 11, 2025
|
Type stability of `Lux.batched_jacobian`
|
|
5
|
112
|
June 10, 2025
|