深層学習異常検出器

深層学習異常検出器の作成とワークフロー

深層学習異常検出器は、自己符号化器など、Deep Learning Toolbox™ で提供されている多層深層学習ネットワークに基づきます。

深層学習アルゴリズムは、異常を検出する代わりの方法を提供します。一般に計算量が多くなるため、学習に時間がかかります。

アプリ

時系列異常検出器Interactively create, train, test, and tune detectors for detecting anomalous behavior in time series (R2026a 以降)

関数

すべて展開する

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

トピック