This video is part of the Deep Learning Summit, Singapore 2017 Event. If you would like to access all of the videos please click here.

Adversarial Component Analysis

Brian's latest work on adversarial component analysis uses adversarial learning, autoencoders and domain adaptation to prevent overfitting in training deep learning models.

Brian Cheung, PhD Student/ Google Brain Intern at UC Berkeley/ Google

Brian Cheung is a PhD Student at UC Berkeley working with Professor Bruno Olshausen at the Redwood Center for Theoretical Neuroscience. His research interests lie at the intersection between machine learning and neuroscience. Drawing inspiration from these fields, he hopes to create systems which can solve complex vision tasks using attention and memory.