wip
This commit is contained in:
Jan Kowalczyk
196
thesis/Main.bbl
196
thesis/Main.bbl
@@ -596,6 +596,100 @@
|
||||
\verb http://dx.doi.org/10.1016/j.knosys.2021.106878
|
||||
\endverb
|
||||
\endentry
|
||||
\entry{deep_svdd}{inproceedings}{}{}
|
||||
\name{author}{8}{}{%
|
||||
{{hash=002c037bd5c44a3c55a7523254ff0522}{%
|
||||
family={Ruff},
|
||||
familyi={R\bibinitperiod},
|
||||
given={Lukas},
|
||||
giveni={L\bibinitperiod}}}%
|
||||
{{hash=1e584159c8f4d32a1e55772b4b798844}{%
|
||||
family={Vandermeulen},
|
||||
familyi={V\bibinitperiod},
|
||||
given={Robert},
|
||||
giveni={R\bibinitperiod}}}%
|
||||
{{hash=d225927675f1b50ada7afdcd7141a590}{%
|
||||
family={Goernitz},
|
||||
familyi={G\bibinitperiod},
|
||||
given={Nico},
|
||||
giveni={N\bibinitperiod}}}%
|
||||
{{hash=99c57c6d6c2549166bb9eb10bd8357a9}{%
|
||||
family={Deecke},
|
||||
familyi={D\bibinitperiod},
|
||||
given={Lucas},
|
||||
giveni={L\bibinitperiod}}}%
|
||||
{{hash=74815873173614768c79b41ebcd30fb7}{%
|
||||
family={Siddiqui},
|
||||
familyi={S\bibinitperiod},
|
||||
given={Shoaib\bibnamedelima Ahmed},
|
||||
giveni={S\bibinitperiod\bibinitdelim A\bibinitperiod}}}%
|
||||
{{hash=d122a2a87d21da4007f460564975e967}{%
|
||||
family={Binder},
|
||||
familyi={B\bibinitperiod},
|
||||
given={Alexander},
|
||||
giveni={A\bibinitperiod}}}%
|
||||
{{hash=d2949700f8a8fdee1e69d478901c51d7}{%
|
||||
family={Müller},
|
||||
familyi={M\bibinitperiod},
|
||||
given={Emmanuel},
|
||||
giveni={E\bibinitperiod}}}%
|
||||
{{hash=5f7a97296025f5dcf9ed79d67caa64fc}{%
|
||||
family={Kloft},
|
||||
familyi={K\bibinitperiod},
|
||||
given={Marius},
|
||||
giveni={M\bibinitperiod}}}%
|
||||
}
|
||||
\name{editor}{2}{}{%
|
||||
{{hash=dc770b9b0d58d3008bbb3906497d898c}{%
|
||||
family={Dy},
|
||||
familyi={D\bibinitperiod},
|
||||
given={Jennifer},
|
||||
giveni={J\bibinitperiod}}}%
|
||||
{{hash=112eb0b147c4a7f674d015a86e5dea70}{%
|
||||
family={Krause},
|
||||
familyi={K\bibinitperiod},
|
||||
given={Andreas},
|
||||
giveni={A\bibinitperiod}}}%
|
||||
}
|
||||
\list{publisher}{1}{%
|
||||
{PMLR}%
|
||||
}
|
||||
\strng{namehash}{f49556d617d4a5ffe2baa6d71026cde2}
|
||||
\strng{fullhash}{dcbeae0afbfe40f33a90739e660c9b68}
|
||||
\strng{fullhashraw}{dcbeae0afbfe40f33a90739e660c9b68}
|
||||
\strng{bibnamehash}{dcbeae0afbfe40f33a90739e660c9b68}
|
||||
\strng{authorbibnamehash}{dcbeae0afbfe40f33a90739e660c9b68}
|
||||
\strng{authornamehash}{f49556d617d4a5ffe2baa6d71026cde2}
|
||||
\strng{authorfullhash}{dcbeae0afbfe40f33a90739e660c9b68}
|
||||
\strng{authorfullhashraw}{dcbeae0afbfe40f33a90739e660c9b68}
|
||||
\strng{editorbibnamehash}{83be554d58af5be1788b5c3616f0e92a}
|
||||
\strng{editornamehash}{83be554d58af5be1788b5c3616f0e92a}
|
||||
\strng{editorfullhash}{83be554d58af5be1788b5c3616f0e92a}
|
||||
\strng{editorfullhashraw}{83be554d58af5be1788b5c3616f0e92a}
|
||||
\field{extraname}{2}
|
||||
\field{sortinit}{1}
|
||||
\field{sortinithash}{4f6aaa89bab872aa0999fec09ff8e98a}
|
||||
\field{labelnamesource}{author}
|
||||
\field{labeltitlesource}{title}
|
||||
\field{abstract}{Despite the great advances made by deep learning in many machine learning problems, there is a relative dearth of deep learning approaches for anomaly detection. Those approaches which do exist involve networks trained to perform a task other than anomaly detection, namely generative models or compression, which are in turn adapted for use in anomaly detection; they are not trained on an anomaly detection based objective. In this paper we introduce a new anomaly detection method—Deep Support Vector Data Description—, which is trained on an anomaly detection based objective. The adaptation to the deep regime necessitates that our neural network and training procedure satisfy certain properties, which we demonstrate theoretically. We show the effectiveness of our method on MNIST and CIFAR-10 image benchmark datasets as well as on the detection of adversarial examples of GTSRB stop signs.}
|
||||
\field{booktitle}{Proceedings of the 35th International Conference on Machine Learning}
|
||||
\field{month}{10--15 Jul}
|
||||
\field{series}{Proceedings of Machine Learning Research}
|
||||
\field{title}{Deep One-Class Classification}
|
||||
\field{volume}{80}
|
||||
\field{year}{2018}
|
||||
\field{pages}{4393\bibrangedash 4402}
|
||||
\range{pages}{10}
|
||||
\verb{file}
|
||||
\verb http://proceedings.mlr.press/v80/ruff18a/ruff18a.pdf
|
||||
\endverb
|
||||
\verb{urlraw}
|
||||
\verb https://proceedings.mlr.press/v80/ruff18a.html
|
||||
\endverb
|
||||
\verb{url}
|
||||
\verb https://proceedings.mlr.press/v80/ruff18a.html
|
||||
\endverb
|
||||
\endentry
|
||||
\entry{ml_autoencoder_figure_source}{article}{}{}
|
||||
\name{author}{1}{}{%
|
||||
{{hash=49d03d499031db786a0e61119024cf5a}{%
|
||||
@@ -612,8 +706,8 @@
|
||||
\strng{authornamehash}{49d03d499031db786a0e61119024cf5a}
|
||||
\strng{authorfullhash}{49d03d499031db786a0e61119024cf5a}
|
||||
\strng{authorfullhashraw}{49d03d499031db786a0e61119024cf5a}
|
||||
\field{sortinit}{1}
|
||||
\field{sortinithash}{4f6aaa89bab872aa0999fec09ff8e98a}
|
||||
\field{sortinit}{2}
|
||||
\field{sortinithash}{8b555b3791beccb63322c22f3320aa9a}
|
||||
\field{labelnamesource}{author}
|
||||
\field{labeltitlesource}{title}
|
||||
\field{journaltitle}{lilianweng.github.io}
|
||||
@@ -899,8 +993,8 @@
|
||||
\strng{authornamehash}{04b1af8a561822bd2336140b9c47f5ed}
|
||||
\strng{authorfullhash}{e7818c2cd27c283d60a3963ba626342b}
|
||||
\strng{authorfullhashraw}{e7818c2cd27c283d60a3963ba626342b}
|
||||
\field{sortinit}{2}
|
||||
\field{sortinithash}{8b555b3791beccb63322c22f3320aa9a}
|
||||
\field{sortinit}{3}
|
||||
\field{sortinithash}{ad6fe7482ffbd7b9f99c9e8b5dccd3d7}
|
||||
\field{labelnamesource}{author}
|
||||
\field{labeltitlesource}{title}
|
||||
\field{issn}{2379-9153}
|
||||
@@ -1083,100 +1177,6 @@
|
||||
\endverb
|
||||
\keyw{Degradation;Location awareness;Laser radar;Rain;Codes;System performance;Current measurement}
|
||||
\endentry
|
||||
\entry{deepsvdd}{inproceedings}{}{}
|
||||
\name{author}{8}{}{%
|
||||
{{hash=002c037bd5c44a3c55a7523254ff0522}{%
|
||||
family={Ruff},
|
||||
familyi={R\bibinitperiod},
|
||||
given={Lukas},
|
||||
giveni={L\bibinitperiod}}}%
|
||||
{{hash=1e584159c8f4d32a1e55772b4b798844}{%
|
||||
family={Vandermeulen},
|
||||
familyi={V\bibinitperiod},
|
||||
given={Robert},
|
||||
giveni={R\bibinitperiod}}}%
|
||||
{{hash=d225927675f1b50ada7afdcd7141a590}{%
|
||||
family={Goernitz},
|
||||
familyi={G\bibinitperiod},
|
||||
given={Nico},
|
||||
giveni={N\bibinitperiod}}}%
|
||||
{{hash=99c57c6d6c2549166bb9eb10bd8357a9}{%
|
||||
family={Deecke},
|
||||
familyi={D\bibinitperiod},
|
||||
given={Lucas},
|
||||
giveni={L\bibinitperiod}}}%
|
||||
{{hash=74815873173614768c79b41ebcd30fb7}{%
|
||||
family={Siddiqui},
|
||||
familyi={S\bibinitperiod},
|
||||
given={Shoaib\bibnamedelima Ahmed},
|
||||
giveni={S\bibinitperiod\bibinitdelim A\bibinitperiod}}}%
|
||||
{{hash=d122a2a87d21da4007f460564975e967}{%
|
||||
family={Binder},
|
||||
familyi={B\bibinitperiod},
|
||||
given={Alexander},
|
||||
giveni={A\bibinitperiod}}}%
|
||||
{{hash=d2949700f8a8fdee1e69d478901c51d7}{%
|
||||
family={Müller},
|
||||
familyi={M\bibinitperiod},
|
||||
given={Emmanuel},
|
||||
giveni={E\bibinitperiod}}}%
|
||||
{{hash=5f7a97296025f5dcf9ed79d67caa64fc}{%
|
||||
family={Kloft},
|
||||
familyi={K\bibinitperiod},
|
||||
given={Marius},
|
||||
giveni={M\bibinitperiod}}}%
|
||||
}
|
||||
\name{editor}{2}{}{%
|
||||
{{hash=dc770b9b0d58d3008bbb3906497d898c}{%
|
||||
family={Dy},
|
||||
familyi={D\bibinitperiod},
|
||||
given={Jennifer},
|
||||
giveni={J\bibinitperiod}}}%
|
||||
{{hash=112eb0b147c4a7f674d015a86e5dea70}{%
|
||||
family={Krause},
|
||||
familyi={K\bibinitperiod},
|
||||
given={Andreas},
|
||||
giveni={A\bibinitperiod}}}%
|
||||
}
|
||||
\list{publisher}{1}{%
|
||||
{PMLR}%
|
||||
}
|
||||
\strng{namehash}{f49556d617d4a5ffe2baa6d71026cde2}
|
||||
\strng{fullhash}{dcbeae0afbfe40f33a90739e660c9b68}
|
||||
\strng{fullhashraw}{dcbeae0afbfe40f33a90739e660c9b68}
|
||||
\strng{bibnamehash}{dcbeae0afbfe40f33a90739e660c9b68}
|
||||
\strng{authorbibnamehash}{dcbeae0afbfe40f33a90739e660c9b68}
|
||||
\strng{authornamehash}{f49556d617d4a5ffe2baa6d71026cde2}
|
||||
\strng{authorfullhash}{dcbeae0afbfe40f33a90739e660c9b68}
|
||||
\strng{authorfullhashraw}{dcbeae0afbfe40f33a90739e660c9b68}
|
||||
\strng{editorbibnamehash}{83be554d58af5be1788b5c3616f0e92a}
|
||||
\strng{editornamehash}{83be554d58af5be1788b5c3616f0e92a}
|
||||
\strng{editorfullhash}{83be554d58af5be1788b5c3616f0e92a}
|
||||
\strng{editorfullhashraw}{83be554d58af5be1788b5c3616f0e92a}
|
||||
\field{extraname}{2}
|
||||
\field{sortinit}{4}
|
||||
\field{sortinithash}{9381316451d1b9788675a07e972a12a7}
|
||||
\field{labelnamesource}{author}
|
||||
\field{labeltitlesource}{title}
|
||||
\field{abstract}{Despite the great advances made by deep learning in many machine learning problems, there is a relative dearth of deep learning approaches for anomaly detection. Those approaches which do exist involve networks trained to perform a task other than anomaly detection, namely generative models or compression, which are in turn adapted for use in anomaly detection; they are not trained on an anomaly detection based objective. In this paper we introduce a new anomaly detection method—Deep Support Vector Data Description—, which is trained on an anomaly detection based objective. The adaptation to the deep regime necessitates that our neural network and training procedure satisfy certain properties, which we demonstrate theoretically. We show the effectiveness of our method on MNIST and CIFAR-10 image benchmark datasets as well as on the detection of adversarial examples of GTSRB stop signs.}
|
||||
\field{booktitle}{Proceedings of the 35th International Conference on Machine Learning}
|
||||
\field{month}{10--15 Jul}
|
||||
\field{series}{Proceedings of Machine Learning Research}
|
||||
\field{title}{Deep One-Class Classification}
|
||||
\field{volume}{80}
|
||||
\field{year}{2018}
|
||||
\field{pages}{4393\bibrangedash 4402}
|
||||
\range{pages}{10}
|
||||
\verb{file}
|
||||
\verb http://proceedings.mlr.press/v80/ruff18a/ruff18a.pdf
|
||||
\endverb
|
||||
\verb{urlraw}
|
||||
\verb https://proceedings.mlr.press/v80/ruff18a.html
|
||||
\endverb
|
||||
\verb{url}
|
||||
\verb https://proceedings.mlr.press/v80/ruff18a.html
|
||||
\endverb
|
||||
\endentry
|
||||
\entry{deep_learning_book}{book}{}{}
|
||||
\name{author}{3}{}{%
|
||||
{{hash=5d2585c11210cf1d4512e6e0a03ec315}{%
|
||||
|
||||
Reference in New Issue
Block a user