This page contains a list of software for scientific machine learning.
To add new entries or amend existing ones, please contact any of the team members.
TensorFlow: https://www.tensorflow.org/
PyTorch: https://pytorch.org/
Keras: https://keras.io/
scikit-learn: https://scikit-learn.org/
MATLAB: https://www.mathworks.com/products/matlab.html
TensorFlow: https://www.tensorflow.org/tutorials
PyTorch: https://pytorch.org/tutorials/
Keras: https://keras.io/getting_started/intro_to_keras_for_researchers/
scikit-learn: https://scikit-learn.org/stable/user_guide.html
MATLAB: Mastering Machine Learning: A step-by-Step Guide with Matlab
SciML - Open source software for scientific machine learning
Deep BSDE solver in TensorFlow
https://github.com/frankhan91/DeepBSDE
DeepXDE, deep learning library for solving differential equations and more
https://github.com/lululxvi/deepxde
Hidden physics models: Machine learning of nonlinear partial differential equations
https://github.com/maziarraissi/HPM
Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
https://github.com/maziarraissi/DeepHPMs
Forward-Backward Stochastic Neural Networks: Deep Learning of High-dimensional Partial Differential Equations
https://github.com/maziarraissi/FBSNNs
Physics Informed Deep Learning: Data-driven Solutions and Discovery of Nonlinear Partial Differential Equations
https://github.com/maziarraissi/PINNs
Hidden Fluid Mechanics
https://github.com/maziarraissi/HFM
Code from "Solving the Parametric Diffusion Equation by Deep Neural Networks - A Numerical Study"
https://github.com/MoGeist/diffusion_PPDE
Shearlab, library for processing two and three dimensional data with shearlets
List: https://www3.math.tu-berlin.de/numerik/www.shearlab.org/software
Applications: https://www3.math.tu-berlin.de/numerik/www.shearlab.org/applications
TensorFlow: https://github.com/arsenal9971/tfshearlab
Julia: https://github.com/arsenal9971/Shearlab.jl
DeNSE, code for "Extraction of digital wavefront sets using applied harmonic analysis and deep neural networks"
Paper: https://arxiv.org/abs/1901.01388
Code: https://github.com/arsenal9971/DeNSE
Kymatio - Wavelet scattering transforms in Python with GPU acceleration
https://github.com/kymatio/kymatio
Operator Discretization Library
https://github.com/odlgroup/odl
prDeep, a noise robust phase retrieval algorithm based on deep neural networks
https://github.com/ricedsp/prDeep
D-AMP Toolbox: Code to run Learned D-AMP, D-AMP, D-VAMP, D-prGAMP, and DnCNN algorithms. It also includes code to train Learned D-AMP, DnCNN, and Deep Image Prior U-net using the SURE loss
https://github.com/ricedsp/D-AMP_Toolbox
Deep-Inverse Correlography: Towards Real-Time High-Resolution Non-Line-of-Sight Imaging
https://github.com/ricedsp/Deep_Inverse_Correlography
DeePMD-kit, A deep learning package for many-body potential energy representation and molecular dynamics
http://www.deepmd.org/
https://github.com/deepmodeling/deepmd-kit
Deep Potential Generator
https://github.com/amcadmus/dpgen
MLFA, Machine Learning Function Approximation
https://github.com/ndexter/MLFA
Implementation of Axon algorithm for function approximation
https://github.com/dashafok/axon-approximation
System recovery, code from "Tensor Network Approaches for Learning Non-Linear Dynamical Laws"
https://github.com/RoteKekse/systemrecovery
Sparse Identification of Nonlinear Dynamics (SINDy)
https://faculty.washington.edu/sbrunton/sparsedynamics.zip
PDE functional identification of nonlinear dynamics (PDE-FIND)
https://github.com/snagcliffs/PDE-FIND
Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems
https://github.com/maziarraissi/MultistepNNs
GMLS-Nets: A Machine Learning Framework for Unstructured Data
PyTorch: https://github.com/atzberg/gmls-nets
TensorFlow: https://github.com/rgp62/gmls-nets
SPGL1 python port
https://github.com/asberk/SPGL1_python_port
DeepHyper: Scalable Asynchronous Neural Architecture and Hyperparameter Search for Deep Neural Networks
https://github.com/deephyper/deephyper