Corpus ID: 43680425

Long Short Term Memory Networks for Anomaly Detection in Time Series

  title={Long Short Term Memory Networks for Anomaly Detection in Time Series},
  author={P. Malhotra and L. Vig and G. Shroff and Puneet Agarwal},
  • P. Malhotra, L. Vig, +1 author Puneet Agarwal
  • Published in ESANN 2015
  • Computer Science
  • Long Short Term Memory (LSTM) networks have been demonstrated to be particularly useful for learning sequences containing longer term patterns of unknown length, due to their ability to maintain long term memory. [...] Key Method A network is trained on non-anomalous data and used as a predictor over a number of time steps. The resulting prediction errors are modeled as a multivariate Gaussian distribution, which is used to assess the likelihood of anomalous behavior. The efficacy of this approach is…Expand Abstract
    Long short-term memory based operation log anomaly detection
    • 25
    LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection
    • 213
    • PDF
    Deep Learning for Time-Series Analysis
    • 125
    • PDF
    Robust Online Time Series Prediction with Recurrent Neural Networks
    • 61
    • PDF
    Hybrid Neural Networks for Learning the Trend in Time Series
    • 50
    • PDF
    Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding
    • 97
    • Highly Influenced
    • PDF


    Publications referenced by this paper.
    Long Short-Term Memory
    • 30,937
    • PDF
    Training and Analysing Deep Recurrent Neural Networks
    • 318
    Detection of abrupt changes: theory and application
    • 3,506
    Static and dynamic novelty detection methods for jet engine health monitoring
    • 65
    • PDF
    How the brain might work: a hierarchical and temporal model for learning and recognition
    • 174
    • PDF
    Online novelty detection on temporal sequences
    • 246
    • PDF