Deep Learning Anomaly Detectors

Creation and workflow for deep learning anomaly detectors

Deep learning anomaly detectors are based on the multilayer deep learning networks provided in Deep Learning Toolbox™, such as autoencoders.

Deep learning algorithms provide an alternative approach to detecting anomalies. They are generally more computationally intensive, and therefore, slower to train.

Apps

Time Series Anomaly DetectorInteractively create, train, test, and tune detectors for detecting anomalous behavior in time series (Since R2026a)

Functions

expand all

tcnADCreate anomaly detector model that uses TCN network to detect anomalies (Since R2025a)
deepantADCreate anomaly detector model that uses CNN network to detect anomalies (Since R2025a)
usADCreate anomaly detector model that uses unsupervised dual-encoder network to detect anomalies in time series (Since R2025a)
vaelstmADCreate anomaly detector model that combines variational autoencoder (VAE) and long short-term memory (LSTM) networks to detect anomalies in time series (Since R2025a)
trainTrain deep learning anomaly detector and obtain detection threshold (Since R2025a)
detectDetect anomalies in time series using trained deep learning detector model (Since R2025a)
updateDetectorUpdate settings of a trained deep learning anomaly detector and recompute detection threshold (Since R2025a)
plotHistogramPlot histogram of anomaly scores and detection threshold for trained deep learning anomaly detector (Since R2025a)
plotPlot detected anomalies and anomaly scores generated from deep learning anomaly detectors (Since R2025a)
timeSeriesAnomalyMetricsCompute specialized evaluation metrics for time series anomaly detection (Since R2026a)
TcnDetectorDetect anomalies in time series using TCN network (Since R2025a)
DeepantDetectorDetect anomalies in time series using deep-learning-based forecasting approach (Since R2025a)
UsadDetectorDetect time series anomalies using unsupervised dual-encoder network (Since R2025a)
VaelstmDetectorDetect anomalies in time series using combined variational autoencoder (VAE) and long short-term memory (LSTM) networks (Since R2025a)
deepSignalAnomalyDetectorCreate signal anomaly detector (Since R2023a)
trainDetectorTrain signal anomaly detector (Since R2023a)
detectDetect anomalies in signals (Since R2023a)
plotAnomaliesPlot signal anomalies (Since R2023a)
updateDetectorUpdate settings of trained detector and recompute detection threshold (Since R2023a)

Topics