Code DAO
Apr 20, 2022 · Artificial Intelligence
Hierarchical Latent Factor Deep Generative Model for Time‑Series Anomaly Detection
The article presents DGHL, a deep generative model that uses a ConvNet generator and alternating back‑propagation to learn hierarchical latent factors for online detection of point and subsequence anomalies in multivariate time‑series, handling missing data and achieving state‑of‑the‑art F1 scores on several benchmark datasets.
alternating backpropagationdeep generative modelhierarchical latent factors
0 likes · 10 min read