Explores the provable benefits of overparameterization in model compression, emphasizing the efficiency of deep neural networks and the importance of retraining for improved performance.
Explores deep learning for autonomous vehicles, covering perception, action, and social forecasting in the context of sensor technologies and ethical considerations.
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.