DiffEqFlux.jl
DiffEqFlux.jl copied to clipboard
SciML
Pre-built implicit layer architectures with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods
These prints don't look very good: ```julia julia> using DiffEqFlux, Flux julia> NeuralODE(Dense(2,2), (0f0,1f0)) (::NeuralODE{Dense{typeof(identity), Matrix{Float32}, Vector{Float32}}, Vector{Float32}, Flux.var"#122#123"{Dense{typeof(identity), Matrix{Float32}, Vector{Float32}}}, Tuple{Float32, Float32}, Tuple{}, Base.Iterators.Pairs{Union{}, Union{}, Tuple{}, NamedTuple{(), Tuple{}}}}) (generic...
It would be great to have more documentations about FFJORD: - [X] Straightforward tutorial - [X] Constructor documentation - [ ] Documentation for arguments - - [ ] `regularize` -...
Really appreciate these packages in SciML. I am now a crazy fan now. I meet some questions while using TensorLayer as a hidden layer. # Q(1) The first problem is...
The paper provides a good method for encoding data with an ODE. This would be useful for being the encoder of an encoder/decoder architecture as an alternative to using an...
My kids currently (~ww33'21) have hand-foot-mouth and I was looking at the papers and articles on the subject to try and get vague sense of how long they will be...
https://discourse.julialang.org/t/what-does-the-maxiters-solver-option-do/37376/13 Environment details: OS: Windows 10 x64 Julia Version : 1.6.0 Packages: - DiffEqFlux v1.39.0 - DiffEqSensitivity v6.52.0 - DifferentialEquations v6.17.1 - Flux v0.12.4 - GalacticOptim v1.3.0 - Optim v1.3.0...
PR adds Liquid Constant Time Layer [#509](https://github.com/SciML/DiffEqFlux.jl/issues/509#issue-830860839). Original [repo1](https://github.com/raminmh/liquid_time_constant_networks) and [repo2](https://github.com/mlech26l/keras-ncp) contain the code which is consistent with biological inspired NCP architecture.  The current implementation differs...
Hi, I got an error when trying to add a function to the chain, and was wondering if there is any way to solve it. The code is following: ```Julia...
https://arxiv.org/abs/2012.06684 @samuela is there code to share that could become a tutorial? I think it would be good to make one.
https://arxiv.org/abs/2006.04439 https://github.com/raminmh/liquid_time_constant_networks