Project Grant R01EB026946

This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) award of $300,000 provided to the Regents of the University of Minnesota aims to develop machine learning models for capturing an agent's dynamic decision-making behavior. The project focuses on learning structural models of control that can better predict how agents, whether human or machine, make decisions over time in changing environments. The research explores...

This $474,000 Project Grant awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program supports research to develop a suite of neural bandit learning algorithms that leverage recent advances in deep learning theory for efficient neural network model training with incomplete feedback. The key objectives are to: 1) Advance bandit learning methods in more complex neural network architectures and explore new deep learning...

This $707,000 National Science Foundation project grant funds the development of a personalized motor learning algorithm at the University of Southern California from August 2022 through July 2025. The university researchers aim to improve motor learning outcomes by generating customized practice schedules for individuals based on a novel algorithm. The algorithm will incorporate each learner's unique attributes and data from other learners to select daily practice doses and schedules that...

This $600,000 National Science Foundation project grant supports research at Stony Brook University to develop a suite of novel distributed reinforcement learning algorithms. The grant is funded through the NSF's Computer and Information Science and Engineering program. Specifically, the three-year award will fund research to establish theoretical foundations for designing, analyzing, and applying fully distributed reinforcement learning algorithms over large-scale networks without global...

This $200,000 National Science Foundation project grant supports the development of data-driven power systems control with stability guarantees. Funded through the NSF Engineering program (CFDA 47.041), the award to Carnegie Mellon University will support three thrusts of collaborative research over a 30-month period ending February 2025. The research aims to design a new framework integrating reinforcement learning algorithms with Lyapunov stability theory to provide stability guarantees for...

This $474,000 federal Project Grant award, issued by the National Science Foundation (NSF) under the Computer and Information Science and Engineering program (CFDA 47.070), supports research to develop neural bandit learning algorithms that leverage deep learning techniques to optimize decision-making in contexts with incomplete feedback. The primary awardee, the University of California, Los Angeles (UCLA), will lead a multi-year research project to bridge the gap between deep learning...

The Massachusetts Institute of Technology (MIT) received a $500,000 Project Grant award from the National Science Foundation Division of Computing and Communication Foundations on June 1, 2022 to support research titled "AF: SMALL: AN ALGORITHMIC THEORY OF BRAIN BEHAVIOR: CONCEPT REPRESENTATION AND LEARNING IN SPIKING NEURAL NETWORKS." The three-year project will investigate concept representation and learning in spiking neural networks through the lens of algorithmic theory. The award...

This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program award of $114,727 to the University of California Irvine (UC Irvine) supports research to develop psychology-aware decision-making algorithms for cyber-physical systems (CPS) that integrate social-psychological dynamics. The goal is to enable harmonious interactions, foster equity, and optimize overall system performance in CPS applications involving multiple humans, such as smart...

This $1.7 million National Science Foundation project grant supports research at West Virginia University and the University of Arkansas, Fayetteville to develop unsupervised continual learning algorithms inspired by neuroplasticity mechanisms observed in electric fish. Funded through NSF's Engineering Directorate (ENG) under the Established Program to Stimulate Competitive Research and Emerging Frontiers in Research and Innovation Brain-Inspired Dynamics for Engineering Energy-Efficient...

This three-year, $300,000 Project Grant from the National Science Foundation Division of Mathematical Sciences under the Mathematical and Physical Sciences program (CFDA 47.049) will support the development of statistical methods for learning the evolution of connectivity in complex time series data. Key products include estimation and inference methods for a Nonstationary Graphical Model framework called NonSTGM that captures nonstationary dynamics in multivariate systems through a sparse...