Bonn 2025 – scientific programme
Parts | Days | Selection | Search | Updates | Downloads | Help
QI: Fachverband Quanteninformation
QI 22: Quantum Simulation
QI 22.3: Talk
Wednesday, March 12, 2025, 15:00–15:15, HS IV
Data Efficient Prediction of Excited State Properties using Quantum Neural Networks — •Manuel Hagelüken1, Marco Huber1,2, and Marco Roth1 — 1Fraunhofer Institute for Manufacturing Engineering and Automation IPA, Nobelstraße 12, D-70569 Stuttgart, Germany — 2Institute of Industrial Manufacturing and Management IFF, University of Stuttgart, Allmandring 35, Stuttgart, 70569, Germany
Understanding the properties of excited states of complex molecules is crucial for many chemical and physical processes. Calculating these properties on quantum computers is often significantly more resource-intensive than calculating their ground state counterparts. We present a quantum machine learning model that combines a symmetry-invariant quantum neural network and a conventional neural network to predict observables of interest for different molecular configurations. The model is trained directly on the molecular ground state wave function, which allows for accurate prediction of excited state properties using only a few training data points. The proposed procedure is fully NISQ compatible. This is achieved through a QNN that requires a number of parameters linearly proportional to the number of molecular orbitals and a parameterized measurement observable, reducing the number of necessary measurements. We benchmark the algorithm on three different molecules by evaluating its performance in predicting excited state transition energies and transition dipole moments. We show that in many instances, the procedure is able to outperform various classical models that rely only on classical features.
Keywords: Excited State Properties; Quantum Neural Network; Quantum Machine Learning; Wave Function; Molecules