Project Grant 2515171
Award Date
7/1/25
Completion Date
6/30/28
Dollars Obligated
$175K
Federal Agency
Division of Mathematical Sciences
Federal Grant Program
47.049
Assistance Type
Project Grant
Place of Performance
Urbana, IL 61801, USA
Similar Awards
This Project Grant from the National Science Foundation's Division of Information and Intelligent Systems, under the Computer and Information Science and Engineering federal grant program (CFDA 47.070), provides $1,127,925 to Carnegie Mellon University for research titled "Foundations of Self-Supervised Learning through the Lens of Probabilistic Generative Models." The research aims to develop scientific and mathematical foundations for self-supervised learning by analyzing aspects...
This $200,000 Project Grant award from the National Science Foundation (NSF) Division of Mathematical Sciences under the Mathematical and Physical Sciences program (CFDA 47.049) aims to develop novel feature selection techniques for supervised and unsupervised machine learning models. The research will focus on the "knockoff method" for identifying key predictive features while controlling false discoveries, incorporating microbiome data structures, handling missing values, and...
This $400,000 federal Project Grant award from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) supports research to develop a principled and unified mathematical framework for deep learning on low-dimensional data structures. The project aims to bridge the gap between theory and practice of deep learning by designing "white-box" deep neural networks using unrolled optimization schemes to maximize information gain in...
This Project Grant from the National Science Foundation Division of Information and Intelligent Systems, under the Computer and Information Science and Engineering federal grant program (CFDA 47.070), provides $169,938 to support research in self-supervised visual representation learning using mixed labeled and unlabeled data. Specifically, the University of California, Davis will study novel self-supervised learning algorithms that can learn rich visual features from unlabeled images and videos...
This $379,999 Project Grant award from the National Science Foundation's (NSF) Division of Mathematical Sciences is funding the development of novel graph-based semi-supervised machine learning techniques that can effectively learn from limited labeled data. The project aims to address the challenge of scarce labeled data in many machine learning applications by incorporating a graph-based semi-supervised learning framework. Specifically, the research encompasses three key objectives: (1)...
The National Science Foundation awarded a $245,043 Project Grant to Carnegie Mellon University under the Computer and Information Science and Engineering federal grant program (CFDA 47.070). The five-year award will support research towards theoretical foundations of neural network-based representation learning. Specifically, the awardee will build a comprehensive theory for new neural network representation learning techniques. This includes characterizing statistical properties of...
This $229,461 Project Grant award from the National Science Foundation's Mathematical and Physical Sciences program (CFDA 47.049) supports the development and analysis of novel self-supervised probabilistic graph structure learning models. The goal is to uncover latent representations hidden within large datasets, which can provide valuable insights across diverse applications like cancer research and environmental analysis. The research will involve creating advanced mathematical models,...
This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Award (CFDA 47.070) provides $400,000 in funding to the University of California, Berkeley to conduct collaborative research on developing a principled and unified mathematical framework for deep learning on low-dimensional data structures. The key objectives are to: 1) Design "white-box" deep neural networks using optimized representation learning techniques to maximize...
This $500,000 Project Grant award from the National Science Foundation's Division of Mathematical Sciences supports the development of novel deep learning techniques for interpretable survival analysis of complex longitudinal healthcare data. The project aims to create a unified deep learning model that can effectively analyze multi-modal data, such as text, images, and lab values, collected at irregular intervals to predict patient outcomes. Key objectives include providing a unified feature...
This federal Project Grant award of $240,000.00 from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) is supporting research at Yale University to develop new computational frameworks that combine large language models with operator learning techniques. The goal is to address key challenges in modeling spatiotemporal phenomena in biomedical research, with applications in areas such as personalized medicine,...