Memory-augmented Adversarial Autoencoders for Multivariate Time-series Anomaly Detection with Deep Reconstruction and Prediction

no code implementations • 15 Oct 2021 • Qinfeng Xiao, Shikuan Shao, Jing Wang

Recent progress of unsupervised time-series anomaly detection mainly use deep autoencoders to solve this problem, i. e. training on normal samples and producing significant reconstruction error on abnormal inputs.

Time Series Time Series Anomaly Detection +1