New blog post: Machine learning with hard constraints: Neural Differential-Algebraic Equations (DAEs) as a general formalism.
#sciml #ai4science #hardconstraints #neuralnetworks #dae #acausal #modelingtoolkit #julialang #modelica
#SciML
Earn money working on open source software #oss! New project just posted: help make wrappers to connect Symbolics.jl to SymPy. $300 bounty. Information for signing up for the #SciML small grants program are contained in the link:
https://sciml.ai/small_grants/#create_wrapper_functions_to_sympy_for_symbolicsjl_300
New blog post: How chaotic is chaos? How some AI for Science / SciML papers are overstating accuracy claims.
Solving physics-based initial value problems with unsupervised machine learning
🔗: https://journals.aps.org/pre/abstract/10.1103/PhysRevE.111.055302
(Open access)
Check out the paper 👉 [https://arxiv.org/pdf/2504.15240](https://arxiv.org/pdf/2504.15240)
#MachineLearning #AI #UncertaintyQuantification #KANs #ConformalPrediction #SciML #Research
---
Let me know if you want it more technical or with emojis toned down!
If you work in controls, you know: write C code for real-time embedded hardware. You can't use #python or #rstats etc. for that, right? With #julialang v1.12, we demonstrate it's possible to ahead of time compile to small binaries for use in controls applications. #sciml
Using higher order automatic differentiation to improve stiff ODE solvers? Using a third order Newton-like method (Halley's) inside the #sciml #julialang ODE solvers with Taylor-mode AD, ~25% faster. This shows a path for non-standard automatic differentiation to become standard within numerical algorithms and is an example of symbolic-numeric programming outperforming standard numerical algorithms. See the manuscript for details!
arxiv.org/abs/2501.16895
The problem of building neural surrogates #sciml for real-world industrial problems is not a problem of choosing neural network architectures, it's a problem of gathering the right training data from the model you're seeking to emulate. We demonstrate this on a turbofan jet engine, achieving 0.1% relative error through an active learning process. This is one of the demonstrations from #scitech showcasing the advancements of industrialization of #SciML
Details: arxiv.org/abs/2501.07701
New fully adaptive Radau IIA method, achieves state-of-the-art performance for high accuracy on highly stiff ODEs. It has a fully automated order construction with adaptive order, and thus if you use higher precision numbers it can automatically construct 17th, 21st, etc. order versions of the method on the fly. Outperforms the classic Hairer Fortran implementation of radau by about 2x across the board!
For more details see: https://arxiv.org/abs/2412.14362 #julialang #sciml
New version of a very good ODE solver today! IRKGaussLegendre released a SIMD and multithreaded mode. 16th order Implicit Runge-Kutta integrator IRKGL16 for non-stiff symplectic equations which require high accuracy.
For more benchmarks, see https://github.com/SciML/IRKGaussLegendre.jl/blob/master/Benchmarks/NLS-WorkPrecision.ipynb
Great work by Minghan Yang as part of her Mary Lister McCammon fellowship.
She implemented a survival model based on a system of ODEs, using @julialanguage coupled with @TuringLang for posterior sampling.
https://github.com/MinghanYang1224/MaryListerMcCammon-Project
#politics news is getting on top of me today. To calm down I watched some videos explaining how to implement #stochasticdifferentialequations in #julialang.
Thanks, #SciML -- I needed a break.
🚨 Preprint alert 🚨
Excited to share this review paper, after a massive effort led by Facu Sapienza. We hope this will help advance the fusion of scientific models and data through differentiable programming.
👇
https://arxiv.org/abs/2406.09699
#datascience #sciml #differentiableprogramming #machinelearning
@pumas_ai named Best Clinical Pharmacology Technology Firm by the 9th Annual Biotechnology Awards! This demonstrates the power of translating #julialang #sciml to industrial practice, building a new foundation of clinical pharmacology.
I am very happy to announce the launch of the #SciML Small Grants program! This is an #opensource contributions program to help improve the #julialang #sciml organization and some of the issues that have traditionally been overlooked. No numerical/scientific knowledge needed for many of these projects. If you've been looking contribute and needed an impetus to get started, let this be your call to arms!
For more information, see https://sciml.ai/small_grants/
Наукове машинне навчання (SciML) — це нова дисципліна, що об’єднує машинне навчання, науку про дані та обчислювальне моделювання. SciML використовує потужні алгоритми для прискорення та покращення наукових досліджень у різних галузях, таких як біологія, фізика та науки про навколишнє середовище.
Differentiable Metropolis-Hastings: differentiate through Bayesian estimation to optimize models towards achieving desired probabilistic outcomes, with implementation in #julialang (#sciml)
For more information, see https://arxiv.org/abs/2306.07961
New structural identifiability analysis features: automatically reparameterize an ODE system to find the best way to make a system easier to learn with #julialang #SciML differentiable programming!
For more, leave a star at https://github.com/SciML/StructuralIdentifiability.jl and check out the tutorial
Client Info
Server: https://mastodon.social
Version: 2025.04
Repository: https://github.com/cyevgeniy/lmst