This $600,000 Project Grant awarded by the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to advance artificial intelligence (AI) by investigating the mathematical foundations and practical applications of deep learning models. The research focuses on understanding the properties of neural networks that enable them to effectively model complex data distributions and capture intricate dependencies. By analyzing the refined data representations that emerge during training, the project seeks to uncover principles underlying the ability of neural networks to represent and process complex information. This research promises to enhance the understanding of network architectures and their capabilities, with potential applications in areas such as image processing and natural language understanding. The University of Wisconsin - Madison, operating as Research and Sponsored Programs, is the prime awardee for this grant, which has a performance period from December 2024 to November 2027.
Generated 3/4/25, 2:47 AM