The purpose of this site is to host cybertraining materials for Quantum Machine Learning technology. The goal of this cybertraining is to prepare the scientific and engineering research workforce with advanced Quantum Machine Learning technology development knowledge and skills. 

More and more data science research for science and engineering (S&E) is facing the big challenge of analyzing extremely large and fast-growing data. Quantum Machine Learning (QML) applies Quantum Computing (QC) and Quantum Information (QI) to Machine Learning (ML) to address the problems of low precision prediction and long processing time for large scale and complex datasets the traditional Machine Learning (ML) algorithms face. It becomes one of the main streams for Quantum Information Science and Engineering (QISE) applications. There is a high demand to develop a workforce in QML for S&E that can explore, apply, and develop Quantum advanced Cyberinfrastructure (CI) tools for S&E research projects. However, QML is underrepresented in most schools' computing curricula, and there is also a need for hands-on, adoptable QML learning materials and faculty with expertise in QML. Thus, it is necessary to build and expand the capacity for students and faculty in QML as an essential and integral part of QML research and education. 

The goals of this Quantum Machine Learning Cybertraining for Science and Engineering (QML4S&E) project are (i) Train and empower S&E researchers with the QML knowledge and skills for data analysis and enhance their real-world research capability with advanced CI; (ii) Build diverse and interdisciplinary communities of collaborative research support in QML for S&E.  We propose workforce development for QML through (1) Developing an innovative portable hands-on labware integrated into multiple courses and curricula, (2) Enhancing and engaging student learning with active learning approaches, and (3) Broadening dissemination of QML learning through an online repository for advanced interdisciplinary CI users and a browser-based online development environment. The proposed labware will provide a getting started module that covers an overview of the Quantum Infrastructure and QML. It will also include practices for environmental setup and a Hello-World example of applying QC to improve the performance of mathematical functions. The labware will also contain learning modules that cover different topics of QML, including TensorFlow Quantum and PennyLane, Quantum Data Preparation and QML Training Models, QML Performance Analysis, QML vs CML, QML for Cybersecurity, QML applications in Industrial Engineering (IE), and QML applications in Computer Science (CS). Each module supports a hands-on engagement learning cycle, which consists of pre-lab activity for conceptualization, hands-on lab activity for extensive learning experience, and post-add-on lab activity for creative enhancement. The modules will be created using Google Colab. This online platform requires only a web browser for designing, developing, and deploying, allowing students to access and practice the modules remotely anytime and anywhere. All modules are open-source, self-contained, and highly adaptable for students to engage in active, hands-on learning. For the project sustainability, the proposed hands-on modules will be made available on a dedicated website to support a wide range of CI users and a QML4S&E research project community group will be organized at open GitHub to promote long-term QML research for S&E.

QML4S&E will offer (i) on-campus intensive, short-duration webinars and summer training workshops; (ii) engineering and computing conference training/tutorial workshops; (iii) one online self-paced training course. These activities will help promote and enhance the interdisciplinary research collaborations between S&E disciplines such as CS and IE, and better prepare the next-generation workforce with advanced CI. The learning materials will also be integrated into multiple computing courses for underrepresented students through project partner intuitions, including Historically Black Colleges and Universities (HBCUs). The preliminary work has been done to demonstrate the feasibility of this project.