AutoQML: Automated Quantum Machine Learning for Industrial Applications

How can we increase the accessibility of Quantum Computing? This is one of the main questions that the project AutoQML seeks to answer. Machine learning is one of the key areas where quantum computing is expected to provide a significant advantage over classical computers. However, finding professionals with expertise in both quantum computing and machine learning is notoriously difficult. Despite advancements in quantum hardware, this talent gap could hinder the deployment of state-of-the-art quantum machine learning (QML) algorithms in real-world industrial applications. In this talk, we will present a solution on how to overcome this issue. 

AutoQML is a framework that enables the use of QML algorithms with minimal prior knowledge by leveraging automated machine learning techniques. The framework eliminates the complexities of selecting the optimal quantum algorithm and fine-tuning hyperparameters, simplifying the application of QML for customers. The service-oriented cloud solution AutoQML features QML solutions, such as quantum kernel methods and quantum neural networks, designed to solve real-world use cases from industrial partners. The integration of QML algorithms is enabled by sQUlearn, a user-friendly, NISQ-ready Python library dedicated to QML. Developed within the project's framework, sQUlearn seamlessly integrates with AutoQML through its scikit-learn interface, exemplifying ease of use and accessibility. The talk will highlight the core features of the AutoQML framework and demonstrate its applicability to an industrial use case.