Mainz 2026 – wissenschaftliches Programm
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
Q: Fachverband Quantenoptik und Photonik
Q 74: Quantum Information – Concepts and Methods
Q 74.3: Vortrag
Freitag, 6. März 2026, 11:30–11:45, P 10
QuKAN: A Quantum Circuit Born Machine Approach to Quantum Kolmogorov Arnold Networks — •Yannick Werner1,2, Akash Malemath2, Mengxi Liu1, Vitor Fortes Rey1,2, Nikolaos Palaiodimopoulos1,2, Paul Lukowicz1,2, and Maximilian Kiefer-Emmanouilidis1,2 — 1DFKI Kaiserslautern — 2RPTU Kaiserslautern-Landau
Kolmogorov Arnold networks, based on the Kolmogorov Arnold representation theorem, provide a compact alternative to conventional neural networks by placing learnable functions on edges rather than nodes. While highly expressive in classical settings, their potential in quantum machine learning remains largely unexplored. In this work, we present an implementation of these KAN architectures in both hybrid and fully quantum forms using a Quantum Circuit Born Machine. We adapt the KAN transfer using pre-trained residual functions, thereby exploiting the representational power of parametrized quantum circuits. In the hybrid model we combine classical KAN components with quantum subroutines, while the fully quantum version the entire architecture of the residual function is translated to a quantum model. We demonstrate the feasibility, interpretability and performance of the proposed Quantum KAN (QuKAN) architecture.
Keywords: Kolmogorov Arnold Network; Quantum Kolmogorov Arnold Networks; Quantum Machine Learning; Hybrid Quantum Models; Interpretable AI