Modified Layerwise Learning for Data Re-uploading Classifier in High-Energy Physics Event Classification

Abstract

This paper aims to demonstrate the use of modified layerwise learning on a data-reuploading classifier, where the parameterized quantum circuit will be used as a quantum classifier to classify the SUSY dataset. We managed to produce a better result using this approach compared to the previous related research with fewer qubits. We obtained an AUC of 0.849 on a testing dataset with 5000 training and testing samples, trained and tested using a state-vector simulator. We also tested to run the circuit on Rigetti’s Aspen-9 quantum processing unit provided by AWS using the already optimized parameter to predict 2000 samples of the test dataset and obtained an AUC of 0.830.

Type
Publication
2021 International Conference on Quantum Computing and Engineering, Institute of Electrical and Electronics Engineers