Tetriscnn reveals phases of matter using interpretable neural networks
TetrisCNN for interpretable detection of phases of matter from experimental quantum simulator data
Machine Learning
Summary
Identifying phases of matter usually requires knowing what patterns to look for, which can be very challenging without prior knowledge. The authors developed TetrisCNN, a special type of neural network that looks at experimental data and not only detects changes in matter but also explains its decisions using clear mathematical formulas. This method works well even on noisy, real-world data from quantum experiments, helping scientists understand new phases of matter more directly. It combines the power of AI with physical insight, making it easier to discover and describe complex states in quantum systems.
What this means in practice
- •For quantum hardware engineers: Automatically detect and characterize quantum phase transitions from experimental simulator data with clear, interpretable outputs.
- •For machine learning engineers: Develop interpretable models that translate experimental physics data into symbolic formulas to enhance trust and insight in AI decisions.
Authors
Kacper Cybiński, Björn van Zwol, James Enouen, Guillaume Bornet, Thierry Lahaye, Antoine Browaeys, Antoine Georges, Anna Dawid
Abstract
Detecting phases of matter in general relies on identifying the correct order parameter - a task that remains notoriously difficult for unknown transitions and traditionally is guided by physical intuition and educated guess. Neural networks have recently offered an alternative route by locating phase transitions in known models without any a priori physical knowledge. Yet these approaches remain black boxes and only identify phases without elucidating their properties. Moreover, they often struggle when confronted with realistic, noisy experimental data, which constitute the ultimate testbed for automated methods in physics. Here, we bridge these perspectives by introducing TetrisCNN, a convolutional architecture with parallel branches of differently shaped filters, reminiscent of Tetris blocks, that learns sparse, interpretable latent representations directly in terms of spin correlators. Applied to experimental snapshots of two-dimensional Ising and XY quantum simulators measured in multiple bases, the network not only detects phase transitions and crossovers but also expresses its latent representation and decision boundaries as symbolic formulas built from experimentally measurable spin correlators. This framework opens the way to integrating interpretable neural networks with quantum simulators to uncover and understand new phases of matter.