Ethan Wu

Correct sampling

2

Closes #609

QuasiRandomTraining(sampling_alg = SobolSample()) is not working correctly

18

```julia julia> s = NeuralPDE.generate_quasi_random_points(300, [[-1.0,-2.0],[1.0,2.0]], Float64, LatinHypercubeSample()) 2×300 Matrix{Float64}: -1.08 -1.33333 -1.86 -1.49333 … -1.54667 -1.66667 -1.47333 1.35667 1.53667 1.84333 1.07333 1.28 1.66667 1.24667 julia> scatter(s[1,:],s[2,:]) ``` ```julia julia>...

Treating states properly, second encounter

3

I just realized that the recent PR #604 did not fix anything. As `Phi` is a mutable field of immutable `PhysicsInformedNN`. The related source code is a bit messy. Adapting...

Single output with parameter estimation

1

```julia using NeuralPDE, Lux, Optimization, OptimizationOptimJL import ModelingToolkit: Interval @parameters t, x, C @variables u(..) Dxx = Differential(x)^2 Dtt = Differential(t)^2 Dt = Differential(t) eq = Dtt(u(t,x)) ~ C^2*Dxx(u(t,x)) bcs...

Installation failed

3

Thanks for your amazing work! I'm trying to install the repo but I got the following error: ``` PS C:\Users\Luffy\visual-chatgpt> python visual_chatgpt.py ╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮ │...

Unexpected return values of `pullback` on GPU

8

```julia using CUDA, Zygote x = CUDA.rand(2) y = CUDA.rand(2) f(x,y) = broadcast(tuple,x,y) pullback(f, x, y)[1] 2-element CuArray{Tuple{ForwardDiff.Dual{Nothing, Float32, 2}, ForwardDiff.Dual{Nothing, Float32, 2}}, 1, CUDA.Mem.DeviceBuffer}: (Dual{Nothing}(0.19380774,1.0,0.0), Dual{Nothing}(0.0026825257,0.0,1.0)) (Dual{Nothing}(0.28045696,1.0,0.0), Dual{Nothing}(0.62378126,0.0,1.0)) ```...

Incorrect gradient type.

1

In the following code, shouldn't `grad` be of the same type as `x`? ```julia julia> using ComponentArrays, Zygote julia> ps = ComponentArray(weight=rand(3,3)) ComponentVector{Float64}(weight = [0.8258011674811379 0.44981527211623784 0.5507199474580698; 0.28250960116858315 0.42697555461561054 0.22836834345488244;...

[Feature Request] `XBuffer` with static stride

2

### Review Mojo's priorities - [X] I have read the [roadmap and priorities](https://docs.modular.com/mojo/roadmap.html#overall-priorities) and I believe this request falls within the priorities. ### What is your request? The current NDBuffer...

[Feature Request] Enhanced Compile-Time and Runtime Integration for Function Optimization in Mojo

8

### Review Mojo's priorities - [X] I have read the [roadmap and priorities](https://docs.modular.com/mojo/roadmap.html#overall-priorities) and I believe this request falls within the priorities. ### What is your request? ### Introduction The...

Rewrite NeuralPDE

3

If anyone wants to rewrite NeuralPDE, I want to share some of my expectations here, some of which have been reflected in Sophon.jl. The following code is mostly pseudocode, used...