R. Chalapathy, A. Menon, and S. Chawla. (2018)cite arxiv:1802.06360Comment: Submitted, to KDD 2018 - London, United Kingdom. 19 - 23 August 2018.
Abstract
We propose a one-class neural network (OC-NN) model to detect anomalies in
complex data sets. OC-NN combines the ability of deep networks to extract
progressively rich representation of data with the one-class objective of
creating a tight envelope around normal data. The OC-NN approach breaks new
ground for the following crucial reason: data representation in the hidden
layer is driven by the OC-NN objective and is thus customized for anomaly
detection. This is a departure from other approaches which use a hybrid
approach of learning deep features using an autoencoder and then feeding the
features into a separate anomaly detection method like one-class SVM (OC-SVM).
The hybrid OC-SVM approach is suboptimal because it is unable to influence
representational learning in the hidden layers. A comprehensive set of
experiments demonstrate that on complex data sets (like CIFAR and PFAM), OC-NN
significantly outperforms existing state-of-the-art anomaly detection methods.
%0 Generic
%1 chalapathy2018anomaly
%A Chalapathy, Raghavendra
%A Menon, Aditya Krishna
%A Chawla, Sanjay
%D 2018
%K to_read unsupervised
%T Anomaly Detection using One-Class Neural Networks
%U http://arxiv.org/abs/1802.06360
%X We propose a one-class neural network (OC-NN) model to detect anomalies in
complex data sets. OC-NN combines the ability of deep networks to extract
progressively rich representation of data with the one-class objective of
creating a tight envelope around normal data. The OC-NN approach breaks new
ground for the following crucial reason: data representation in the hidden
layer is driven by the OC-NN objective and is thus customized for anomaly
detection. This is a departure from other approaches which use a hybrid
approach of learning deep features using an autoencoder and then feeding the
features into a separate anomaly detection method like one-class SVM (OC-SVM).
The hybrid OC-SVM approach is suboptimal because it is unable to influence
representational learning in the hidden layers. A comprehensive set of
experiments demonstrate that on complex data sets (like CIFAR and PFAM), OC-NN
significantly outperforms existing state-of-the-art anomaly detection methods.
@misc{chalapathy2018anomaly,
abstract = {We propose a one-class neural network (OC-NN) model to detect anomalies in
complex data sets. OC-NN combines the ability of deep networks to extract
progressively rich representation of data with the one-class objective of
creating a tight envelope around normal data. The OC-NN approach breaks new
ground for the following crucial reason: data representation in the hidden
layer is driven by the OC-NN objective and is thus customized for anomaly
detection. This is a departure from other approaches which use a hybrid
approach of learning deep features using an autoencoder and then feeding the
features into a separate anomaly detection method like one-class SVM (OC-SVM).
The hybrid OC-SVM approach is suboptimal because it is unable to influence
representational learning in the hidden layers. A comprehensive set of
experiments demonstrate that on complex data sets (like CIFAR and PFAM), OC-NN
significantly outperforms existing state-of-the-art anomaly detection methods.},
added-at = {2018-02-20T09:59:19.000+0100},
author = {Chalapathy, Raghavendra and Menon, Aditya Krishna and Chawla, Sanjay},
biburl = {https://www.bibsonomy.org/bibtex/242c5eb1506991c91df34a0c4b53725b9/jk_itwm},
description = {Anomaly Detection using One-Class Neural Networks},
interhash = {d8080b9b704d0111a25f5a215148c101},
intrahash = {42c5eb1506991c91df34a0c4b53725b9},
keywords = {to_read unsupervised},
note = {cite arxiv:1802.06360Comment: Submitted, to KDD 2018 - London, United Kingdom. 19 - 23 August 2018},
timestamp = {2018-02-20T09:59:19.000+0100},
title = {Anomaly Detection using One-Class Neural Networks},
url = {http://arxiv.org/abs/1802.06360},
year = 2018
}