Project Grant W911NF2510095

The National Science Foundation (NSF) awarded a $582,031 Project Grant under the Computer and Information Science and Engineering program (CFDA 47.070) to the Regents of the University of Michigan, doing business as the University of Michigan. The grant will fund a 5-year research project focused on "Achieving Explainable Artificial Intelligence (AI) Through Human-AI Interaction." The goal of the project is to develop new scientific knowledge and design guidelines for delivering...

This Project Grant award from the National Science Foundation's STEM Education (CFDA 47.076) program provides $450,000 to Princeton University to develop "Differentiable Logic Networks" - an interpretable and energy-efficient approach to implementing artificial intelligence (AI) and machine learning frameworks. The project aims to address the key challenge of making AI-based decisions more transparent and explainable, particularly for applications in domains like medical and legal...

This Project Grant awarded by the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) will develop new approaches for training artificial intelligence (AI) systems to make their decision-making processes more transparent and interpretable to people. The $175,000 award to New York University (NYU) aims to accomplish two key goals: 1) Develop a theoretical framework that formalizes human interpretability of autonomous...

This Project Grant award from the National Cancer Institute (CFDA 93.393 - Cancer Cause and Prevention Research) provides $266,614 to Rutgers, The State University to develop a principled framework for systematically explaining AI-based histopathological tumor classification models using counterfactual explanations. The project aims to: (1) create a "generative explainer" to generate histopathological images that can lead to a spectrum of model predictions, (2) develop an...

This $300,000 EAGER (Early-concept Grants for Exploratory Research) award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program aims to develop a framework called XAISE (eXplainable Artificial Intelligence for Science and Engineering) to enhance the explainability of artificial intelligence (AI) models for scientific and engineering applications. The project seeks to design, develop, and implement XAISE to improve the explainability of...

This Project Grant from the National Science Foundation's Division of Information and Intelligent Systems, under the Computer and Information Science and Engineering program (CFDA 47.070), provides $576,351 to Purdue University to advance fair and explainable artificial intelligence through new algorithms and human-centered approaches. The award supports research activities from August 15, 2022 to July 31, 2027 to develop a family of fair, explainable, and robust data mining algorithms with...

This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Award (CFDA 47.070) for $119,764 aims to develop a new paradigm of certified explanations for artificial intelligence (AI) systems. The project, titled "CAREER: CERTIFIED EXPLANATIONS FOR TRUSTWORTHY ARTIFICIAL INTELLIGENCE," seeks to bridge the gap between formal verification and explainability to create AI systems with provable assurances that can be relied upon in high-stakes...

This $175,000 two-year Project Grant from the National Science Foundation's Division of Information and Intelligent Systems, under the Computer and Information Science and Engineering program (CFDA 47.070), will fund research at the University of Southern California to develop more explainable artificial intelligence agents with common sense capabilities. The grant aims to advance techniques for AI agents to reason in novel situations, complete open-world narratives, and provide commonsense...

This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) will fund research to develop Algorithm-Informed Neural Networks (AINNs) - a new approach that integrates well-established algorithmic principles into the design of neural networks. The $150,000 award, effective May 1, 2025 through April 30, 2027, will enable the University of Missouri at Kansas City (UMKC) to enhance the explainability, reliability,...

This Project Grant from the National Science Foundation's $524,474 Computer and Information Science and Engineering program will support the development of artificial intelligence systems capable of understanding general real-world tasks and providing step-by-step visual and language guidance to solve complex problems. Over a three-year period from June 2022 to May 2025, researchers at the University of Minnesota will create a new dataset annotating diverse everyday tasks and solutions,...