Deep neural network classifiers typically require large labeled datasets to obtain high predictive performance. Obtaining such datasets can be time and cost prohibitive especially for applications where careful expert labeling is required, for instance, in healthcare and medicine. In this talk, we describe two algorithms using GANs that can help reduce this labeling burden. First, we describe a semi-supervised learning algorithm that utilizes GANs to perform manifold regularization. Our method achieves state-of-the-art performance amongst GAN-based semi-supervised learning methods while being much easier to implement. Second, we describe the Adversarially Learned Anomaly Detection (ALAD) algorithm (based on bi-directional GANs) for unsupervised anomaly detection. ALAD uses reconstruction errors based on adversarially learned features to determine if a data sample is anomalous. ALAD achieves state-of-the-art performance on a range of image and tabular datasets while being several hundred-fold faster at test time than the only published GAN-based method.
日時: 2018年11月26日（月）、14:10 - 14:40
場所: R-CCS 6階講堂
・講演題目：Learning with less labeled data using GANs
・講演者：Foo Chuan Sheng（A*STAR-I2R Programme Head（Precision Medicine）, Scientist（Deep Learning Department））