A discrepancy in self-attention between python and Julia (Transformers)
|
|
7
|
324
|
January 26, 2024
|
GPU memory in Julia
|
|
5
|
207
|
January 25, 2024
|
Forcing Lux to use Enzyme instead of Zygote?
|
|
10
|
292
|
January 25, 2024
|
[English help] An imputer that works with any supervised model, a "GeneralImputer" or a "UniversalImputer" (or other?)
|
|
0
|
92
|
January 24, 2024
|
Inverse problem with NeuralPDE and GPU support
|
|
5
|
214
|
January 23, 2024
|
Issue with Zygote over ForwardDiff.derivative
|
|
10
|
1009
|
January 21, 2024
|
Maliar, Maliar, and Winant using Flux.jl (I just want to write a custom objective)
|
|
8
|
531
|
January 19, 2024
|
Microsoft Phi model
|
|
0
|
138
|
January 17, 2024
|
Is there any julia package for multivariate polynomial regression?
|
|
18
|
649
|
January 16, 2024
|
Learning rate decay in callback function
|
|
3
|
276
|
January 11, 2024
|
DiffEqGPU.jl with CUDA: Error computing gradients through SDE solver
|
|
12
|
166
|
January 10, 2024
|
Differentiation (Zygote, but the issue is likely in ChainRules) return different types with `Diagonal`
|
|
2
|
140
|
January 10, 2024
|
Optimization.jl and Lux.jl 1.10.0 Compatability
|
|
1
|
266
|
January 10, 2024
|
Physics-enhanced deep surrogates for partial differential equations
|
|
0
|
211
|
January 9, 2024
|
How to read model weights using FluxTraining (stateaccess issues)?
|
|
3
|
261
|
January 9, 2024
|
Does Lux work with FluxTraining?
|
|
0
|
137
|
January 9, 2024
|
XGBoostClassifier on bigger than RAM database
|
|
2
|
221
|
January 8, 2024
|
ReversedDiff/Zygote with SDE DifferentialEquations fails to compute gradients after a certain number of parameters
|
|
2
|
181
|
January 7, 2024
|
Lux Loss Not Decreasing
|
|
1
|
231
|
January 4, 2024
|
Why do we need 3 chains to solve a PDE using NeuralPDE
|
|
3
|
372
|
December 30, 2023
|
Understanding and Overcoming Zygote's Functional Limitations for distributed
|
|
5
|
254
|
December 29, 2023
|
I am building a simple to use autoencoder model.. anyone interested?
|
|
4
|
303
|
December 29, 2023
|
Flux loss with contribution gradient is slow
|
|
5
|
395
|
December 27, 2023
|
Higher order derivatives/ automatic differentiation
|
|
5
|
498
|
December 26, 2023
|
PINN using Flux
|
|
4
|
578
|
December 24, 2023
|
Issues with computing gradient with ForwardDiff.jl (Any fixes other than ND?)
|
|
2
|
162
|
December 24, 2023
|
Learning rate scheduler with the new interface of Flux
|
|
4
|
423
|
December 23, 2023
|
Smoothing probability distribution output of network
|
|
3
|
209
|
December 22, 2023
|
Introducing NNUE to the Julia community
|
|
1
|
330
|
December 19, 2023
|
Are there guidelines or rules of thumb on how to stack hidden layers in a RNN?
|
|
5
|
549
|
December 14, 2023
|