This three-year, $276,611 National Science Foundation Project Grant supports research at the University at Albany to develop algorithms and theory for compressing deep neural networks. Funded through NSF's Mathematical and Physical Sciences program (CFDA 47.049), this award will advance knowledge in discrete optimization and machine learning. Key products include new coarse gradient and thresholding algorithms to enable efficient deployment of AI systems on mobile and low-power platforms. By compressing network structure and reducing size, these techniques aim to realize the fast and energy-efficient use of deep learning in applications such as computer vision, robotics, and biometric identification. The grant also supports training of graduate students and development of data science courses to build workforce capacity. Research outcomes have the potential to broaden artificial intelligence's societal impacts by enabling wider adoption on ubiquitous mobile devices.
Generated 1/6/24, 10:12 AM