# Operationally meaningful representations of physical systems in neural networks

arXiv: https://arxiv.org/abs/2001.00593 · HTML: https://mlsanity.com/paper/2001.00593/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jan 2020.

## Built on by (most cited first, 16 of 16)

- [Interpretable Machine Learning in Physics: A Review](https://mlsanity.com/paper/2503.23616/) (2025)
- [Explainable Representation Learning of Small Quantum States](https://mlsanity.com/paper/2306.05694/) (2023)
- [Learning minimal representations of stochastic processes with variational autoencoders](https://mlsanity.com/paper/2307.11608/) (2023)
- [Quantum computing and artificial intelligence: status and perspectives](https://mlsanity.com/paper/2505.23860/) (2025)
- [Interpretable representation learning of quantum data enabled by probabilistic variational autoencoders](https://mlsanity.com/paper/2506.11982/) (2025)
- [Learning Minimal Representations of Many-Body Physics from Snapshots of a Quantum Simulator](https://mlsanity.com/paper/2509.13821/) (2025)
- [Compressed Hierarchical Representations for Multi-Task Learning and Task Clustering](https://mlsanity.com/paper/2205.15882/) (2022)
- [Position Paper on Materials Design -- A Modern Approach](https://mlsanity.com/paper/2312.10996/) (2023)
- [Disentanglement by means of action-induced representations](https://mlsanity.com/paper/2602.06741/) (2026)
- [AI Research Associate for Early-Stage Scientific Discovery](https://mlsanity.com/paper/2202.03199/) (2022)
- [Automated Gadget Discovery in Science](https://mlsanity.com/paper/2212.12743/) (2022)
- [Closed-Form Interpretation of Neural Network Latent Spaces with Symbolic Gradients](https://mlsanity.com/paper/2409.05305/) (2024)
- [Discover physical concepts and equations with machine learning](https://mlsanity.com/paper/2412.12161/) (2024)
- [Sequence-Model-Guided Measurement Selection for Quantum State Learning](https://mlsanity.com/paper/2507.09891/) (2025)
- [Learning Physical Concepts in Cyber-Physical Systems: A Case Study](https://mlsanity.com/paper/2111.14151/) (2021)
- [QILP-0: Constructing Observational Declarative Twins of Quantum Circuits](https://mlsanity.com/paper/2609.01049/) (2026)

## Abstract (arXiv)

To make progress in science, we often build abstract representations of physical systems that meaningfully encode information about the systems. The representations learnt by most current machine learning techniques reflect statistical structure present in the training data; however, these methods do not allow us to specify explicit and operationally meaningful requirements on the representation. Here, we present a neural network architecture based on the notion that agents dealing with different aspects of a physical system should be able to communicate relevant information as efficiently as possible to one another. This produces representations that separate different parameters which are useful for making statements about the physical system in different experimental settings. We present examples involving both classical and quantum physics. For instance, our architecture finds a compact representation of an arbitrary two-qubit system that separates local parameters from parameters describing quantum correlations. We further show that this method can be combined with reinforcement learning to enable representation learning within interactive scenarios where agents need to explore experimental settings to identify relevant variables.