Towards Robust Deep Learning
- Nanyang Ye, University of Cambridge
- Time: 2020-04-05 15:10
- Host: Prof. Yizhou Wang
- Venue: Online Talk
Abstract
Although deep learning has almost become the default choice in many applications, applications, such as autonomous driving, face recognition. The lack of deep learning theory makes it dangerous to apply it for critical applications. We do not yet have a convincing theory on when will the deep learning works or fails. For example, we can easily fool the traffic sign recognition systems by putting some small white or black strips on the signs. And the face recognition system can easily fail if we wear specially designed glasses. The method to fail deep learning systems is usually referred to as the adversarial attack. This talk is about my research on improving the generalization and robustness of deep learning systems via the lens of Bayesian theory. Besides, I will also demonstrate the application of deep learning for visually lossless image compression.
Biography
Dr. Nanyang Ye is a recently graduated PhD from University of Cambridge. His research interests include but not limited to the safety of machine learning, Bayesian deep learning, and deep learning application in computer graphics.