Project Grant 2223793
- This $1,999,112 project grant from the National Science Foundation's Engineering Directorate (NSF ENG) will fund research at The Johns Hopkins University to develop new artificial intelligence techniques inspired by neuroscience models of visual attention. Specifically, the grant aims to translate models of visual attention in mammalian brains into new deep learning algorithms that can greatly reduce the number of variables updated during machine learning. If successful, these brain-inspired...
- The National Science Foundation (NSF) awarded a $174,229 Project Grant under the Computer and Information Science and Engineering (CISE) program to Michigan Technological University. The grant, awarded on October 1, 2023, with a completion date of September 30, 2025, is focused on developing a self-learning neuromorphic robot system that can operate efficiently in resource-constrained environments. The key objectives of this research project are to: 1) create a neuromorphic robot that utilizes...
- This $618,159 National Science Foundation project grant supports research into developing energy-efficient hardware and software for machine learning and artificial intelligence systems. Funded under the Computer and Information Science and Engineering program, the award supports The Washington University in investigating frameworks using quantum-tunneling dynamic-analog memory devices and novel online learning algorithms. Specific objectives include exploring Fowler-Nordheim dynamic analog...
- This $298,710 Project Grant from the National Science Foundation's Division of Computer and Network Systems, under the Computer and Information Science and Engineering program (CFDA 47.070), will fund research towards developing a bio-inspired cyber-physical system for optimal robot locomotion in fluids. The Pennsylvania State University will receive funding to create a pressure-sensitive synthetic skin for robotic fish, along with control and learning algorithms using the distributed pressure...
- 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...
- The National Science Foundation Division of Electrical, Communications and Cyber Systems awarded a $500,000 Project Grant to Texas A&M Engineering Experiment Station, doing business as Tees, to support research towards a principled framework for resilient, data efficient and scalable reinforcement learning for control. The award period is from February 1, 2021 through January 31, 2026. The research is funded under the NSF Directorate for Engineering's Engineering program (CFDA 47.041), which...
- This National Science Foundation (NSF) grant award under the Computer and Information Science and Engineering program (CFDA 47.070) provides $250,000 over 3 years to Northeastern University, a private non-profit research university based in Boston, MA, to develop advanced techniques for continual online learning on energy-constrained edge computing devices. The key products and services to be delivered through this research project include: (1) an attention-guided smart layer freezing approach...
- This $1.6 million Project Grant from the National Science Foundation's Computer and Information Science and Engineering program will fund research at the University of Pennsylvania from October 2022 through September 2026. The research focuses on developing theoretical tools to build an understanding of why deep neural networks (DNNs) work and when they can fail. Investigators will seek to identify common themes in how artificial and biological systems like the human brain learn. They will...
- The National Science Foundation Division of Integrative Organismal Systems awarded a $980,000 Project Grant to The Washington University to support research examining neuronal plasticity and the evolvability of behavior through September 2026. Funded under the Biological Sciences program (CFDA 47.074), this award will allow researchers to test the hypothesis that activity-dependent wiring changes in response to altered sensory feedback drive coordinated modifications between peripheral organs...
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 Circuits and Artificial Intelligence programs, this four-year award aims to endow autonomous systems with the adaptability of biological systems. Specifically, the researchers will study hierarchical timescales and plasticity principles in the cerebellar pathways of electric fish to inform the design of machine learning approaches enabling data-driven adaptation and knowledge retention in autonomous agents processing continuous, multimodal data streams without interruption for manual training. Overcoming challenges around data efficiency, flexibility in learning and forgetting rates, and generating representations from multiple modalities could support new levels of resilience in real-time autonomous systems operating in open-world environments.
Mod # | Description | ReasonForModification | Federal Obligation | Date |
|---|---|---|---|---|
| Not listed | $1.7m | 9/16/22 |