In this talk, I explore whether artificial intelligence can autonomously recover known structures of the Standard Model of particle physics using only experimental data and no theoretical input. By applying unsupervised machine learning techniques—such as dimensionality reduction and clustering—to intrinsic particle properties and decay modes, we find that key features of particle physics emerge directly from the data. These include the relative strength of interactions, the distinction between baryons and mesons, and conserved quantities such as baryon number, strangeness, and charm. The analysis also reveals the isospin structure, the Eightfold Way multiplets, and signatures of Regge trajectories in baryon excitations. I will also discuss how these approaches can be extended to capture deeper symmetry patterns and internal structures.
