ml4science

This repository is the official implementation of the paper Convolutional Neural Operators for robust and accurate learning of PDEs

Increase citations, ease review & collaboration A collection of "easy wins" to make machine learning in research reproducible. This tutorial focuses on basics that work. Getting you 90% of the way to top-tier reproducibility.

Near-linear scaling neural PDE solver for large unstructured meshes via multi-scale attention with ball-tree partitioning

「機械学習による分子最適化」のサポートページ

[ICLR 2025] This is the official repository for the paper “A Unified Framework for Forward and Inverse Problems in Subsurface Imaging Using Latent Space Translations." This work proposes a generalized framework to solve forward and inverse problems, utilizing the latent space. We also propose an invertible architecture for the OpenFWI dataset.

Graph Feedforward Network (GFN) - a novel neural network layer for resolution-invariant machine learning

Graph Feedforward Networks: a resolution-invariant generalisation of feedforward networks for graphical data, applied to model order reduction

ResNet-15 Architecture for classifying electrons and photons using data from high energy physics detector at CERN's LHC.

This repository is the official implementation of the paper "RONOM: Reduced-Order Neural Operator Modeling" published in the SIAM Journal on Scientific Computing

agentification_of_hep_analysis_pipeline