The National Science Foundation (NSF) awarded a $596,797 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) program to the University of California, San Diego (UCSD) to develop interpretable and robust deep neural network models for safety-critical applications. The project aims to create automated methods for interpreting the internal functioning of deep neural networks using human-understandable concepts, learn intrinsically interpretable models, and quantify the reliability and robustness of the generated interpretations and neural network models. The goal is to promote transparency, reliability, and trustworthiness in the deployment of deep learning technologies in critical domains. The award period runs from September 1, 2024 to August 31, 2027.
Generated 2/25/25, 3:38 AM