Introduces a functional framework for deep neural networks with adaptive piecewise-linear splines, focusing on biomedical image reconstruction and the challenges of deep splines.
Explores physics-informed imaging systems, including lensless imaging, deep learning for imaging challenges, and the development of noise models for low-light videos.
Explores neural networks' ability to learn features and make linear predictions, emphasizing the importance of data quantity for effective performance.
Explores the provable benefits of overparameterization in model compression, emphasizing the efficiency of deep neural networks and the importance of retraining for improved performance.
