SymPhysAI

AI offers novel methodologies to unravel complex physical phenomena. However, most machine learning models lack transparency in their decision-making processes. In this SymPhysAI project, we aim to develop a symbolic AI to reveal hidden topological orders in quantum physics. To this end, an AI-assisted symbolic regression method will be studied. ¹

Specifically, we focus on three main objectives:

1. Machine learning topological phases with experimental data.
2. Uncovering hidden non-local symmetry-protected topological orders.
3. Searching for quantized topological invariants in an unsupervised fashion.

The interplay between symbolic AI and quantum physics is envisioned to bring new insights into topological phases. Moreover, we will scrutinize the explainability and the robustness of machine learning models. The outcomes of the SymPhysAI project will pave the way to discover novel features of topological materials in a reliable and explainable way.

I have been the primary coordinator contact for the SymPhysAI project at MagTop, IF PAN since July 2024. I invite you to follow my popular-science blog for insights and updates on our research journey.