Title: Machine Learning for Adaptive Interventions
Abstract: The last decade of research in mobile health has seen extensive use of machine learning methods to develop computational biomarkers and detectors for a wide array of activities and states. Simultaneously, there has been increasing use of reinforcement learning methods as a mechanism for personalizing adaptive intervention policies in areas such as physical activity promotion and support for smoking cessation, as well as increasing interest in including machine learning-based biomarkers among the adaptive intervention tailoring variables. This talk will explore questions at the intersection of these lines of work including the impact of machine learning-based context inference uncertainty and interaction scarcity on the ability to learn effective adaptive intervention policies, and the potential for large language models to help offset some of these challenges.
Bio: Benjamin M. Marlin is a professor in the Manning College of Information and Computer Sciences at the University of Massachusetts Amherst. His research focuses on the development of probabilistic and deep learning models for time series data with applications to clinical and mobile health data analytics and the Internet of Things. He also works on the development of embedded and distributed learning systems for supporting real-time data analysis. His work has been supported by the National Science Foundation, the National Institutes of Health, the Patient-Centered Outcomes Research Institute, the US Army Research Lab, and the Intelligence Advanced Research Projects Activity. Marlin currently serves as Associate Director for the Massachusetts AI and Technology Center for Connected Care in Aging and Alzheimer’s Disease (MassAITC), an NIA-funded Artificial Intelligence and Technology Collaboratory that has awarded over 30 pilot projects since its establishment in 2021. Marlin completed his PhD in computer science at the University of Toronto and was a postdoctoral fellow at the University of British Columbia before joining UMass Amherst.