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...
The Massachusetts Institute of Technology (MIT) received a $108,000 Project Grant award from the National Science Foundation Division of Computing and Communication Foundations to support collaboration research on probabilistic, geometric, and topological analysis of neural networks from theory to applications. The two-year award, issued on January 1, 2022 and set to conclude on December 31, 2024, will fund research under the Mathematical and Physical Sciences program (CFDA #47.049). This...
The National Science Foundation (NSF) awarded a $240,000 Project Grant under the Mathematical and Physical Sciences program (CFDA 47.049) to the University of Central Florida (UCF) Board of Trustees Office of Research. The grant supports a 3-year research project to develop a theoretical analysis that sheds light on the robustness of neural network-based methods and the properties of adversarial training. The research aims to contribute to the development of more robust neural network-based...
Trustees of Boston College received a $299,860 Project Grant award from the National Science Foundation Division of Computing and Communication Foundations on January 1, 2022 for collaborative research titled "Probabilistic, Geometric, and Topological Analysis of Neural Networks, from Theory to Applications." The research is being conducted under the Mathematical and Physical Sciences program (CFDA 47.049) to advance understanding of major problems in these scientific fields and...
The National Science Foundation (NSF) Division of Mathematical Sciences awarded a $107,860 Project Grant to the Regents of the University of Minnesota, Office of Sponsored Projects Administration, a non-profit 1862 land grant college, to conduct research under the NSF Mathematical and Physical Sciences program (CFDA 47.049). The research project will develop theoretical foundations for using machine learning methods to solve high-dimensional partial differential equations, emphasizing...
This $300,000 Project Grant award from the National Science Foundation's (NSF) Mathematical and Physical Sciences (CFDA 47.049) program supports the development of a new mathematical framework for the Nash embedding theorems, which are foundational to key scientific challenges in areas like fluid turbulence and deep learning.
The primary objectives are to rigorously analyze Riemannian Langevin equations to construct Gibbs measures and develop fast optimization and sampling algorithms. This...
The Massachusetts Institute of Technology (MIT) received a $600,000 Project Grant award from the National Science Foundation (NSF) on December 1, 2021 to fund research titled "COLLABORATIVE RESEARCH: FOUNDATIONS OF DEEP LEARNING: THEORY, ROBUSTNESS, AND THE BRAIN?" through November 30, 2024. The award is part of the NSF's Mathematical and Physical Sciences program (CFDA 47.049), which aims to promote progress in these scientific fields and strengthen the national scientific...
This Project Grant award from the National Science Foundation Division of Mathematical Sciences provides $155,046 to the University of Massachusetts Amherst under the Mathematical and Physical Sciences federal grant program (CFDA 47.049) from September 2021 through August 2023.
The funding supports applied research in the areas of geometry and harmonic analysis to develop new regularization techniques for deep learning models. By drawing from pure mathematics disciplines, the grantee aims to...
This $296,555 Project Grant from the National Science Foundation's (NSF) Mathematical and Physical Sciences program (CFDA 47.049) will support the development of reduced basis enhancements for neural networks and their application to quantum materials simulation. Specifically, the University of Massachusetts Dartmouth will combine traditional reduced basis methods with deep learning techniques to build an analysis-driven computational emulator for parameterized partial differential equations....
The Trustees of the University of Pennsylvania received a $275,000 project grant from the National Science Foundation's Mathematical and Physical Sciences program (CFDA 47.049) to conduct research on geometrization approaches toward understanding deep learning. Specifically, the three-year award funds research projects analyzing symmetries in trained deep neural networks, examining dynamics of deep learning training, and investigating how deep learning separates data across neural network...