Generative Adversarial Networks

Adversarial Regularized Reconstruction for Anomaly Detection and Generation

We propose ARN, a semisupervised anomaly detection and generation method based on adversarial reconstruction. ARN exploits a regularized autoencoder to optimize the reconstruction of variants of normal examples with minimal differences, that are …

Machine learning methods for generating high dimensional discrete datasets

The development of platforms and techniques for emerging Big Data and Machine Learning applications requires the availability of real-life datasets. A possible solution is to synthesize datasets that reflect patterns of real ones using a two-step …