The best repository showing why transformers might not be the answer for time series forecasting and showcasing the best SOTA non transformer models.

Reduced order models using invariance principles

Loss Patterns of Neural Networks

A benchmark fault diagnosis dataset comprises vibration data collected from a gearbox under variable working conditions with intentionally induced faults, encompassing diverse fault severities and …

GenAI Processors is a lightweight Python library that enables efficient, parallel content processing.

Samples for Intel® oneAPI Toolkits

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

🎨 Diagram as Code for prototyping cloud system architectures

A comprehensive collection of KAN(Kolmogorov-Arnold Network)-related resources, including libraries, projects, tutorials, papers, and more, for researchers and developers in the Kolmogorov-Arnold N…

Examples in the MLX framework

MLX: An array framework for Apple silicon

Tensors and Dynamic neural networks in Python with strong GPU acceleration

The Fast Cross-Platform Package Manager

ME 539 - Introduction to Scientific Machine Learning

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

A library for scientific machine learning and physics-informed learning

⚡ TabPFN: Foundation Model for Tabular Data ⚡

Pytorch-based framework for solving parametric constrained optimization problems, physics-informed system identification, and parametric model predictive control.

Jupyter notebook tutorials on various machine learning topics

Chemical reaction network and systems biology interface for scientific machine learning (SciML). High performance, GPU-parallelized, and O(1) solvers in open source software.

Course 18.S191 at MIT, Fall 2022 - Introduction to computational thinking with Julia

Simulation, visualization, and inference of individual level infectious disease models with Julia

Physics-informed learning of governing equations from scarce data

SciML glacier model

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

18.S096 - Applications of Scientific Machine Learning

Multi-language suite for high-performance solvers of differential equations and scientific machine learning (SciML) components. Ordinary differential equations (ODEs), stochastic differential equat…

Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/

18.337 - Parallel Computing and Scientific Machine Learning

Extensible, Efficient Quantum Algorithm Design for Humans.