Speaker
Description
Particle identification is one of most fundamental tools in various HEP experiments. For the BESIII experiment on the BEPCII, the realization of numerous physical goals heavily relies on advanced particle identification algorithms. In recent years, the emerging of quantum machine learning could potentially arm HEP experiments with a powerful new toolbox. In this proposal, targeting at the PID problem at BESIII, we are developing quantum classifiers based on quantum machine learning algorithms under the Noisy Intermediate-Scale Quantum (NISQ) device. The first algorithm we developed is a SVM classifier based on quantum kernel methods, while the second algorithm we are developing is a variational quantum classifier, also known as a quantum neural network. For the quantum SVM classifier, we mainly study the expressiveness of different feature maps by optimizing the encoding circutis, while for the quantum neural network, we mainly study different variational circuits and optimization methods. By simulating these models using the IBM quantum simulator, as well as deploying the models to the Wuyuan quantum hardware system, we found that the quantum classifiers show comparable discrimination power with other traditional machine learning models. This has demonstrated the potential of using quantum machine learning techniques to form a new approach for particle identification in HEP experiments.
| CERN group or section submitting a project proposal | ATLAS |
|---|
