Quantum-inspired Machine Learning

The aim of the talk is to introduce a new quantum-like method for the binary classification applied to classical datasets. Inspired by the quantum Helstrom measurement, this approach enables to define a new binary classifier, called Helstrom Quantum Classifier (HQC). This classifier (inspired by the concept of distinguishability between quantum states) acts on density matrices — called density patterns — that are the quantum encoding of classical patterns of a dataset. We compare the performance of HQC with respect to several standard classifiers over different datasets and we show that HQC outperforms the other classifiers when compared to the Balanced Accuracy and other significant statistical measures. We also show that the performance of our classifier is positively correlated to the increase in the number of “quantum copies” of a pattern and the resulting tensor product thereof. In the last part of the talk we show a large-scale experiment based on the application of HQC to the biomedical imaging context in clonogenic assay evaluation to identify the most discriminative feature, allowing us to enhance cell colony segmentation.

Zoom link: https://univr.zoom.us/j/87646180055
Contact Person: Alessandra Di Pierro