Quantum-Inspired Machine Learning Methods for Anomaly Detection

Using simplified language understandable to a layperson, provide a general, one-paragraph description of the proposed research project to be undertaken by the intern(s) as well as the expected benefit to the partner organization. (100-150 words)
In this project, we will develop quantum and quantum-inspired machine learning models for anomaly detection applications. We will build statistical models based on tensor networks and density matrices of quantum systems, which will be trained on available data to tell normal data samples (like healthy X-rays scans, or normal credit card transactions) from anomalous (like unhealthy X-ray scans or fraudulent transactions??. We will utilize quantum physics-inspired methods, which offer a novel and advanced way to address these tasks. We will test our models on a variety of anomaly detection tasks including health-related tasks, financial fraud detection, manufacturing monitoring, etc. We will identify the most compelling use cases where our models bring the most advantage. Upon successful execution of this project, we will publish our results in a machine learning journal and will promote our results to be used in real-life applications so that society can directly benefit from the basic science advances.??

Faculty Supervisor:

Guillaume Rabusseau

Student:

Partner:

Zapata Canada

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

Université de Montréal

Program: