# Inferring physical laws by artificial intelligence based causal models

arXiv: https://arxiv.org/abs/2309.04069 · HTML: https://mlsanity.com/paper/2309.04069/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 74 references that are in the map.
- First posted on arXiv 8 Sep 2023.

## Builds on (most cited first, 8 of 8)

- [AI Feynman: a Physics-Inspired Method for Symbolic Regression](https://mlsanity.com/paper/1905.11481/) (2019)
- [Discovering physical concepts with neural networks](https://mlsanity.com/paper/1807.10300/) (2018)
- [DoWhy: An End-to-End Library for Causal Inference](https://mlsanity.com/paper/2011.04216/) (2020)
- [Discovering Phase Transitions with Unsupervised Learning](https://mlsanity.com/paper/1606.00318/) (2016)
- [Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines](https://mlsanity.com/paper/1610.02746/) (2016)
- [Learning Thermodynamics with Boltzmann Machines](https://mlsanity.com/paper/1606.02718/) (2016)
- [Learning Interpretable Representations of Entanglement in Quantum Optics Experiments using Deep Generative Models](https://mlsanity.com/paper/2109.02490/) (2021)
- [Scientific intuition inspired by machine learning generated hypotheses](https://mlsanity.com/paper/2010.14236/) (2020)

## Abstract (arXiv)

The advances in Artificial Intelligence (AI) and Machine Learning (ML) have opened up many avenues for scientific research, and are adding new dimensions to the process of knowledge creation. However, even the most powerful and versatile of ML applications till date are primarily in the domain of analysis of associations and boil down to complex data fitting. Judea Pearl has pointed out that Artificial General Intelligence must involve interventions involving the acts of doing and imagining. Any machine assisted scientific discovery thus must include casual analysis and interventions. In this context, we propose a causal learning model of physical principles, which not only recognizes correlations but also brings out casual relationships. We use the principles of causal inference and interventions to study the cause-and-effect relationships in the context of some well-known physical phenomena. We show that this technique can not only figure out associations among data, but is also able to correctly ascertain the cause-and-effect relations amongst the variables, thereby strengthening (or weakening) our confidence in the proposed model of the underlying physical process.