ai-hilbert

AI Hilbert is an algebraic geometric based discovery system (based on Putinar's Positivstellensatz), that enables the discovery of fundamental laws of nature (or non-physical systems) based on knowledge (articulated in formal logic terms) and experimental data.

https://github.com/ibm/ai-hilbert

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
    Found 3 DOI reference(s) in README
  • Academic publication links
    Links to: nature.com, zenodo.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (8.4%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

AI Hilbert is an algebraic geometric based discovery system (based on Putinar's Positivstellensatz), that enables the discovery of fundamental laws of nature (or non-physical systems) based on knowledge (articulated in formal logic terms) and experimental data.

Basic Info
Statistics
  • Stars: 31
  • Watchers: 4
  • Forks: 6
  • Open Issues: 0
  • Releases: 2
Created almost 2 years ago · Last pushed over 1 year ago
Metadata Files
Readme License Citation

README.md

GitHub tag DOI License: MIT

AI-Hilbert

This repository contains the code and the data used for the experiments in the paper Evolving Scientific Discovery by Unifying Data and Background Knowledge with AI Hilbert published in Nature Communications.

AI Hilbert is an algebraic geometric based discovery system (based on Putinar's Positivstellensatz), that enables the discovery of fundamental laws of nature (or non-physical systems) based on knowledge (articulated in formal logic terms) and experimental data.

Visit our website for a general overview, references, and some introductory videos: → AI-Hilbert website

system overview

Code

The code is organized in 3 folders. One containing the problems studied in the main paper, one containing the problems studied in the paper appendix and one for data generation.

The folder main_problems contains: * A notebook for the Hagen-Poissuille Equation, Einstein’s Relativistic Time Dilation Law and Kepler’s Third Law of Planetary Motion: hageneinsteinkepler[3.3][3.5][3.6].ipynb * A folder for the revisited problem of deriving Kepler’s third law of planetary motion from an incomplete background theory keplerwithmissing_axioms[3.7] containing: * the corresponding notebook keplerwithmissing_axioms[3.7].ipynb * the data used data_kepler.dat, datakeplerd.dat, and datakeplern_points.dat. * A notebook for the Radiated Gravitational Wave Power Equation: grav_waves[3.4].ipynb * A notebook for the Bell Inequalities: bell_inequalities[3.8].ipynb

The folder suppl_material_problems contains a notebook for each of the following problems: * 6 problems from FSRD (Feynman Symbolic Regression Database based on "The Feynman Lectures on Physics"): * I.15.10 FSRD: I1510.ipynb * I.27.6 FSRD: I276.ipynb * I.34.8 FSRD: I348.ipynb * I.43.16 FSRD: I4316.ipynb * II.10.9 FSRD: II109.ipynb * II.34.2 FSRD: II342.ipynb * 6 additional problems: * Inelastic Relativistic Collision: inelastic.ipynb * Decay of Pion into Muon and Neutrino: decay.ipynb * Radiation Damping and Light Scattering: light.ipynb * Escape Velocity: escape.ipynb * Hall Effect: hall.ipynb * Compton Scattering: compton.ipynb

The folder data_generation contains: * A python file for generating the data for the Kepler problem datagenkepler.py * A python file datagenmix.py for generating the data for the following problems: * Inelastic Relativistic Collision * Decay of Pion into Muon and Neutrino * Radiation Damping and Light Scattering * Escape Velocity * Hall Effect * Compton Scattering * Radiation Gravitational Wave Power * Hagen Poiseuille equation

How to cite

@article{AI_Hilbert, title={Evolving scientific discovery by unifying data and background knowledge with AI Hilbert}, author={Ryan Cory-Wright and Cristina Cornelio and Sanjeeb Dash and Bachir El Khadir and Lior Horesh}, volume = {15}, url = {https://doi.org/10.1038/s41467-024-50074-w}, doi = {10.1038/s41467-024-50074-w}, journal = {Nature Communications}, month = jul, year = {2024}, pages = {5922}, }

Owner

  • Name: International Business Machines
  • Login: IBM
  • Kind: organization
  • Email: awesome@ibm.com
  • Location: United States of America

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- given-names: "Ryan"
  family-names: "Cory-Wright"
- given-names: "Cristina"
  family-names: "Cornelio"
- given-names: "Sanjeeb"
  family-names: "Dash"
- given-names: "Bachir"
  family-names: "El Khadir"
- given-names: "Lior"
  family-names: "Horesh"
title: "[AI-Hilbert GitHub Repository], Evolving Scientific Discovery by Unifying Data and Background Knowledge with AI Hilbert"
version: 1.0.1
doi: 10.5281/zenodo.11453179
date-released: 2024-6-3
url: "https://github.com/IBM/AI-Hilbert"

GitHub Events

Total
  • Watch event: 10
  • Fork event: 1
Last Year
  • Watch event: 10
  • Fork event: 1