Unsupervised Anomaly Detection With LSTM Neural Networks

@article{Ergen2020UnsupervisedAD,
  title={Unsupervised Anomaly Detection With LSTM Neural Networks},
  author={Tolga Ergen and S. Kozat},
  journal={IEEE Transactions on Neural Networks and Learning Systems},
  year={2020},
  volume={31},
  pages={3127-3141}
}
  • Tolga Ergen, S. Kozat
  • Published 2020
  • Computer Science, Engineering, Mathematics, Medicine
  • IEEE Transactions on Neural Networks and Learning Systems
We investigate anomaly detection in an unsupervised framework and introduce Long Short Term Memory (LSTM) neural network based algorithms. [...] Key Method As the first time in the literature, we jointly train and optimize the parameters of the LSTM architecture and the OC-SVM (or SVDD) algorithm using highly effective gradient and quadratic programming based training methods.Expand
42 Citations
Unsupervised Anomaly Detection via Deep Metric Learning with End-to-End Optimization
  • 1
  • PDF
One-step Predictive Encoder - Gaussian Segment Model for Time Series Anomaly Detection
  • Highly Influenced
  • PDF
Combining OC-SVMs With LSTM for Detecting Anomalies in Telemetry Data With Irregular Intervals
  • PDF
A novel distributed anomaly detection algorithm based on support vector machines
  • 2
Deep anomaly detection for industrial systems: a case study
  • PDF
Deep Semi-Supervised Anomaly Detection
  • 64
  • PDF
Deep Variational Semi-Supervised Novelty Detection
  • 5
  • PDF
ESAD: End-to-end Deep Semi-supervised Anomaly Detection
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 52 REFERENCES
Efficient Unsupervised Parameter Estimation for One-Class Support Vector Machines
  • 29
  • PDF
Toward Supervised Anomaly Detection
  • 183
  • PDF
Network Anomaly Detection Using One Class Support Vector Machine
  • 25
  • PDF
Long Short Term Memory Networks for Anomaly Detection in Time Series
  • 620
  • Highly Influential
  • PDF
Time-series novelty detection using one-class support vector machines
  • J. Ma, S. Perkins
  • Mathematics
  • Proceedings of the International Joint Conference on Neural Networks, 2003.
  • 2003
  • 242
  • Highly Influential
One class support vector machine for anomaly detection in the communication network performance data
  • 35
Online Training of LSTM Networks in Distributed Systems for Variable Length Data Sequences
  • Tolga Ergen, S. Kozat
  • Computer Science, Engineering
  • IEEE Transactions on Neural Networks and Learning Systems
  • 2018
  • 29
  • PDF
LSTM: A Search Space Odyssey
  • 2,459
  • PDF
A generative-discriminative framework for time-series data classification
  • 2
Novelty Detection Using Level Set Methods
  • 21
  • PDF
...
1
2
3
4
5
...