Project Grant 80NSSC24K0876

This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program grant awarded to North Carolina State University (NC State) provides $208,745 to develop scalable and stable neural network paradigms to address variability issues in emerging device-based platforms for large-scale neuromorphic computing. The project aims to improve the reliability and sustainability of deep learning accelerators for data centers by explicitly modeling weight uncertainties,...

This $298,450 National Science Foundation project grant supports research to quantify the error landscape of deep neural networks. Funded under the Computer and Information Science and Engineering program (CFDA 47.070), the awardee New York University will employ statistical mechanics methods to characterize the basins of attraction in high-dimensional parameter spaces of deep learning models. The university will measure basin volume distributions and flatness as a function of network parameters...

This Project Grant from the National Science Foundation's Division of Undergraduate Education aims to advance Bayesian thinking in STEM fields through curriculum development and instructor training. Funded under the NSF IUSE: EHR and IUSE:HSI programs, total funding is $136,769. Specifically, a consortium led by the University of California Irvine will develop and offer a professional development program focused on teaching Bayesian methods. The program includes a week-long instructor boot...

This two-year, $250,000 Project Grant from the National Science Foundation's Computer and Information Science and Engineering program aims to develop techniques for improving the interpretability and robustness of deep neural networks. Specifically, the University of California, Santa Barbara will apply ideas from communication theory and neuroscience to actively shape the features extracted by individual layers of neural networks in addition to end-to-end training. By learning "matched...

This four-year $800,000 Project Grant from the National Science Foundation's (NSF) Computer and Information Science and Engineering program (CFDA 47.070) will support research at the University of California, Los Angeles (UCLA) to develop theoretical tools for understanding deep neural networks (DNNs). The research aims to identify common themes in how artificial and biological systems like the human brain learn. It will investigate the hypothesis that DNNs succeed when learning tasks exhibit...

This four-year, $622,992 project grant from the National Science Foundation's Computer and Information Science and Engineering program aims to develop methods for making machine learning models more interpretable and reliable. Specifically, researchers at the University of Virginia will investigate the mathematical foundations of deep neural networks, with a focus on geometry and topology, to better understand internal representations. Computational tools will be designed based on these...

This three-year Project Grant from the National Science Foundation's Division of Computing and Communication Foundations will fund the development of analysis and design techniques to provide formally guaranteed error bounds for deep neural networks used in autonomous cyber-physical systems. Totaling $999,996, the award will support research from June 2022 to May 2025. Specifically, the University of California, Los Angeles will investigate two approaches - "correctness-by-training"...

This three-year, $674,542 National Science Foundation project grant supports research at the University of California Santa Cruz to develop Bayesian statistical and machine learning methods for analyzing complex survey data from the federal statistical system. The grant falls under the NSF's Social, Behavioral, and Economic Sciences program (CFDA 47.075), which promotes basic research and education in these fields. Specifically, the investigators will extend existing models using data...

The National Science Foundation (NSF) awarded a $225,000 Project Grant under the Mathematical and Physical Sciences (CFDA 47.049) program to The Leland Stanford Junior University. The 3-year grant, effective July 1, 2024, aims to gain a deeper theoretical understanding of the statistical properties of neural networks, which have revolutionized science and engineering. Key research directions include studying the distinguishing features of deep neural networks compared to classical statistical...

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...