Help training a NN that's used as a parameter in an ODE
|
|
1
|
87
|
May 22, 2025
|
Using a trained MLJ model for prediction on non-Table objects
|
|
1
|
55
|
May 18, 2025
|
How to embed expert knowledge /constraints in ML training?
|
|
11
|
210
|
May 16, 2025
|
New package for clustering - need for an arXiv endorser
|
|
2
|
274
|
May 15, 2025
|
Are forward-mode derivatives calculated in parallel?
|
|
1
|
102
|
May 9, 2025
|
Error when running Code on GPU
|
|
0
|
49
|
May 5, 2025
|
Type-stable function with Flux Chain and Dense
|
|
3
|
104
|
May 4, 2025
|
Error when a neural ode is implemented
|
|
3
|
143
|
May 2, 2025
|
Best libraries for experimenting with small scale models?
|
|
7
|
387
|
April 25, 2025
|
Memory usage increasing with each epoch
|
|
18
|
761
|
April 14, 2025
|
What is the status of ReinforcementLearning.jl
|
|
24
|
934
|
April 8, 2025
|
Custom Optimisers and Projections in Flux/Zygote: Is There a Canonical Way?
|
|
1
|
70
|
April 5, 2025
|
Automatic Differentiation for existing AMG libraries
|
|
3
|
96
|
April 4, 2025
|
Run the Gemma 2 9B LLM in Julia and without a GPU?
|
|
5
|
374
|
April 2, 2025
|
Reactant cannot find GPU device
|
|
2
|
186
|
March 19, 2025
|
How can large language models work with julia?
|
|
4
|
316
|
March 18, 2025
|
Lux & Reactant on Colab TPUs
|
|
2
|
403
|
March 16, 2025
|
Best way to prevent AD to differentiate through useless or zero gradient function
|
|
2
|
184
|
March 13, 2025
|
Lux + Enzyme and Zygote + NeuralODE, segmentation fault
|
|
6
|
319
|
March 3, 2025
|
GPU backend-agnostic way to create efficiently random number on the GPU
|
|
3
|
128
|
March 3, 2025
|
Resetting some states in a batch in Lux.jl recurrent layers
|
|
0
|
69
|
February 27, 2025
|
Implementing a ConvNet that doesn't allocate during inference (SimpleChains.jl?)
|
|
3
|
139
|
February 27, 2025
|
Help using cuDNN in Julia
|
|
1
|
82
|
February 25, 2025
|
Training Universal PINNs using NeuralPDE?
|
|
4
|
193
|
February 18, 2025
|
Distributed Data Parallel training with 2 GPUs fails with Flux.jl on AMD GPUs
|
|
7
|
120
|
February 18, 2025
|
DimensionMismatch with MLJ
|
|
0
|
40
|
February 14, 2025
|
RAGTools (from PromptingTools.jl) – Seeking Your Feedback on Next Steps
|
|
8
|
371
|
February 9, 2025
|
Save model when training with Distributed Data Parallel
|
|
0
|
64
|
February 11, 2025
|
Will Reactant.jl become a machine learning framework?
|
|
14
|
1939
|
February 10, 2025
|
Custom loss functions in `Lux.jl`
|
|
5
|
312
|
February 10, 2025
|