Adversarial learning plays a major role in computer security.
Increasing popular in deep learning, adversarial learning aims to enable the safe adoption of machine learning techniques in adversarial settings such as malware detection, biometric recognition, and spam filtering.At the Deep Learning Summit, Singapore, that took place month, Brian Cheung presented his latest work with adversarial component analysis. By treating overfitting as an adversarial problem, Brian uses adversarial component analysis to prevent it. Watch his presentation here:
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.
Watch more videos from the summit here.