@inproceedings{10.1145/2689746.2689747,
  title = {Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction},
  booktitle = {Proceedings of the {{MLSDA}} 2014 2nd Workshop on Machine Learning for Sensory Data Analysis},
  author = {Sakurada, Mayu and Yairi, Takehisa},
  year = {2014},
  series = {{{MLSDA}}'14},
  pages = {4--11},
  publisher = {{Association for Computing Machinery}},
  address = {{New York, NY, USA}},
  doi = {10.1145/2689746.2689747},
  abstract = {This paper proposes to use autoencoders with nonlinear dimensionality reduction in the anomaly detection task. The authors apply dimensionality reduction by using an autoencoder onto both artificial data and real data, and compare it with linear PCA and kernel PCA to clarify its property. The artificial data is generated from Lorenz system, and the real data is the spacecrafts' telemetry data. This paper demonstrates that autoencoders are able to detect subtle anomalies which linear PCA fails. Also, autoencoders can increase their accuracy by extending them to denoising autoenconders. Moreover, autoencoders can be useful as nonlinear techniques without complex computation as kernel PCA requires. Finaly, the authors examine the learned features in the hidden layer of autoencoders, and present that autoencoders learn the normal state properly and activate differently with anomalous input.},
  isbn = {978-1-4503-3159-3},
  keywords = {anomaly detection,auto-assosiative neural network,autoencoder,denoising autoencoder,dimensionality reduction,fault detection,nonlinear,novelty detection,spacecrafts}
}

{"_id":"Q6Adonf7nHAGjDdRv","bibbaseid":"sakurada-yairi-anomalydetectionusingautoencoderswithnonlineardimensionalityreduction-2014","author_short":["Sakurada, M.","Yairi, T."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction","booktitle":"Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis","author":[{"propositions":[],"lastnames":["Sakurada"],"firstnames":["Mayu"],"suffixes":[]},{"propositions":[],"lastnames":["Yairi"],"firstnames":["Takehisa"],"suffixes":[]}],"year":"2014","series":"MLSDA'14","pages":"4–11","publisher":"Association for Computing Machinery","address":"New York, NY, USA","doi":"10.1145/2689746.2689747","abstract":"This paper proposes to use autoencoders with nonlinear dimensionality reduction in the anomaly detection task. The authors apply dimensionality reduction by using an autoencoder onto both artificial data and real data, and compare it with linear PCA and kernel PCA to clarify its property. The artificial data is generated from Lorenz system, and the real data is the spacecrafts' telemetry data. This paper demonstrates that autoencoders are able to detect subtle anomalies which linear PCA fails. Also, autoencoders can increase their accuracy by extending them to denoising autoenconders. Moreover, autoencoders can be useful as nonlinear techniques without complex computation as kernel PCA requires. Finaly, the authors examine the learned features in the hidden layer of autoencoders, and present that autoencoders learn the normal state properly and activate differently with anomalous input.","isbn":"978-1-4503-3159-3","keywords":"anomaly detection,auto-assosiative neural network,autoencoder,denoising autoencoder,dimensionality reduction,fault detection,nonlinear,novelty detection,spacecrafts","bibtex":"@inproceedings{10.1145/2689746.2689747,\r\n title = {Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction},\r\n booktitle = {Proceedings of the {{MLSDA}} 2014 2nd Workshop on Machine Learning for Sensory Data Analysis},\r\n author = {Sakurada, Mayu and Yairi, Takehisa},\r\n year = {2014},\r\n series = {{{MLSDA}}'14},\r\n pages = {4--11},\r\n publisher = {{Association for Computing Machinery}},\r\n address = {{New York, NY, USA}},\r\n doi = {10.1145/2689746.2689747},\r\n abstract = {This paper proposes to use autoencoders with nonlinear dimensionality reduction in the anomaly detection task. The authors apply dimensionality reduction by using an autoencoder onto both artificial data and real data, and compare it with linear PCA and kernel PCA to clarify its property. The artificial data is generated from Lorenz system, and the real data is the spacecrafts' telemetry data. This paper demonstrates that autoencoders are able to detect subtle anomalies which linear PCA fails. Also, autoencoders can increase their accuracy by extending them to denoising autoenconders. Moreover, autoencoders can be useful as nonlinear techniques without complex computation as kernel PCA requires. Finaly, the authors examine the learned features in the hidden layer of autoencoders, and present that autoencoders learn the normal state properly and activate differently with anomalous input.},\r\n isbn = {978-1-4503-3159-3},\r\n keywords = {anomaly detection,auto-assosiative neural network,autoencoder,denoising autoencoder,dimensionality reduction,fault detection,nonlinear,novelty detection,spacecrafts}\r\n}\r\n","author_short":["Sakurada, M.","Yairi, T."],"key":"10.1145/2689746.2689747","id":"10.1145/2689746.2689747","bibbaseid":"sakurada-yairi-anomalydetectionusingautoencoderswithnonlineardimensionalityreduction-2014","role":"author","urls":{},"keyword":["anomaly detection","auto-assosiative neural network","autoencoder","denoising autoencoder","dimensionality reduction","fault detection","nonlinear","novelty detection","spacecrafts"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/network/files/hGdFsR44ctvkxby5m","dataSources":["hdXt5FfDdECL7h3jX"],"keywords":["anomaly detection","auto-assosiative neural network","autoencoder","denoising autoencoder","dimensionality reduction","fault detection","nonlinear","novelty detection","spacecrafts"],"search_terms":["anomaly","detection","using","autoencoders","nonlinear","dimensionality","reduction","sakurada","yairi"],"title":"Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction","year":2014}