Project Grant 2515482
- This Project Grant award from the National Science Foundation's Engineering program (CFDA 47.041) in the amount of $544,381 provides funding to the Regents of the University of Minnesota to develop a principled framework for continual learning, consisting of novel theoretical insights and practical algorithmic designs. The overarching goal is to pioneer methodological advancements in continual learning to empower autonomous machine learners navigating dynamic data environments. The research will...
- This Project Grant award from the National Science Foundation's (NSF) Engineering program (CFDA 47.041) provides $250,000 to The Ohio State University to develop an online bilevel optimization framework for accelerated learning in time-varying environments. The primary objectives are to (i) speed up online bilevel algorithms, improve their scalability, and ensure their performance, and (ii) explore two real-world applications to leverage the advantages of online bilevel optimization in solving...
- The National Science Foundation (NSF) awarded a $175,000 Project Grant under the Computer and Information Science and Engineering (CISE) program to the University of North Carolina at Charlotte. The project, titled "CRII: CSR: ENABLING ON-DEVICE CONTINUAL LEARNING THROUGH ENHANCING EFFICIENCY OF COMPUTING, MEMORY, AND DATA", aims to develop an efficient on-device continual learning framework that can incrementally learn new knowledge without forgetting prior learnt knowledge, while...
- This National Science Foundation (NSF) Engineering program (CFDA 47.041) Project Grant award in the amount of $293,288 aims to combine the advantages of match-based and error-based learning to overcome scalability and credit assignment problems in machine learning models. The project seeks to improve the explainability of Adaptive Resonance Theory (ART) by designing appropriate training templates, and distinguish between catastrophic forgetting and valid performance degradation due to new...
- This $400,000 federal Project Grant award was provided by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) program (CFDA 47.070) to The Ohio State University. The grant supports collaborative research to develop 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 optimized for information gain and representation...
- This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program aims to advance artificial intelligence (AI) by investigating the mathematical foundations and practical applications of deep learning models. The $600,000 award, with a performance period from December 2024 to November 2027, will support research focused on understanding the properties of neural networks, the function spaces and data representations that emerge...
- This $499,999 federal Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) will support collaborative research to investigate the theoretical foundations of compositional learning in large language models (LLMs) based on transformer architectures. The research aims to advance the understanding of how LLMs, such as GPT-4, LLAMA 2, and CLAUDE 3, can decompose complex tasks into simpler intermediate steps to...
- This National Science Foundation (NSF) Project Grant award under the Engineering program (CFDA 47.041) aims to transform the way artificial intelligence (AI) transfers learned knowledge from simulated environments to real-world applications. The $249,999 project, awarded on June 1, 2025, with a completion date of May 31, 2028, will develop a novel neuro-symbolic framework that integrates advanced hyperdimensional computing and symbolic reasoning. This approach will enable transparent and...
- The National Science Foundation (NSF) awarded a $500,000 Project Grant under the Engineering program (CFDA 47.041) to Wayne State University, located in Detroit, Michigan. The goal of this 5-year research project, which commenced on October 1, 2025, is to investigate fundamental limits and algorithmic principles for trustworthy sequential decision-making in artificial intelligence and machine learning (AI/ML) systems, particularly those powered by reinforcement learning. The research focuses...
- This $570,000 Project Grant awarded by the National Science Foundation's (NSF) Division of Mathematical Sciences under the Mathematical and Physical Sciences grant program (CFDA 47.049) supports the development of artificial intelligence (AI) solutions for heterogeneous transfer and personalized federated learning to address mathematical and computing challenges in creating a digital twin for unmanned aerial vehicles (UAVs). The research team at The Ohio State University, which has extensive...
This Project Grant award of $517,498 from the National Science Foundation's Engineering program (CFDA 47.041) will fund research by The Ohio State University from October 1, 2025 to September 30, 2028. The project aims to advance the fundamental understanding of continual learning, which enables artificial intelligence (AI) systems to learn new skills over time without forgetting previous knowledge. The key focus areas include: (i) developing and optimizing sequential replay algorithms to outperform existing continual learning methods, especially for dissimilar tasks; (ii) analyzing catastrophic forgetting and generalization performance in transformer-based models for time-varying classification tasks; and (iii) investigating how transformers' in-context learning abilities impact knowledge transfer and retention. This research will help establish a rigorous theoretical framework for understanding continual learning and inform the design of more adaptive, reliable AI systems across a variety of applications, from robotics to scientific discovery.
Mod # | Description | ReasonForModification | Federal Obligation | Date |
|---|---|---|---|---|
| Not listed | $517.5k | 7/30/25 |