You are about to undo an edit. Please check the comparison below to verify that this is what you want to do, then publish the changes below to finish undoing the edit. If you are undoing an edit that is not vandalism, explain the reason in the edit summary. Do not use the default message only. |
Latest revision | Your text | ||
Line 164: | Line 164: | ||
=== Anomaly detection === |
=== Anomaly detection === |
||
Another application for autoencoders is [[anomaly detection]].<ref name=":13" /><ref>{{Cite book |last1=Morales-Forero |first1=A. |last2=Bassetto |first2=S. |title=2019 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM) |chapter=Case Study: A Semi-Supervised Methodology for Anomaly Detection and Diagnosis |date=December 2019 |chapter-url=https://ieeexplore.ieee.org/document/8978509 |location=Macao, Macao |publisher=IEEE |pages=1031–1037 |doi=10.1109/IEEM44572.2019.8978509 |isbn=978-1-7281-3804-6|s2cid=211027131 }}</ref><ref>{{Cite book |last1=Sakurada |first1=Mayu |last2=Yairi |first2=Takehisa |title=Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis |chapter=Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction |date=December 2014 |chapter-url=http://dl.acm.org/citation.cfm?doid=2689746.2689747 |language=en |location=Gold Coast, Australia QLD, Australia |publisher=ACM Press |pages=4–11 |doi=10.1145/2689746.2689747 |isbn=978-1-4503-3159-3|s2cid=14613395 }}</ref><ref name=":8">An, J., & Cho, S. (2015). [http://dm.snu.ac.kr/static/docs/TR/SNUDM-TR-2015-03.pdf Variational Autoencoder based Anomaly Detection using Reconstruction Probability]. ''Special Lecture on IE'', ''2'', 1-18.</ref><ref>{{Cite book |last1=Zhou |first1=Chong |last2=Paffenroth |first2=Randy C. |title=Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining |chapter=Anomaly Detection with Robust Deep Autoencoders |date=2017-08-04 |chapter-url=https://dl.acm.org/doi/10.1145/3097983.3098052 |language=en |publisher=ACM |pages=665–674 |doi=10.1145/3097983.3098052 |isbn=978-1-4503-4887-4|s2cid=207557733 }}</ref><ref>{{Cite journal|doi=10.1016/j.patrec.2017.07.016|title=A study of deep convolutional auto-encoders for anomaly detection in videos|year=2018|last1=Ribeiro|first1=Manassés|last2=Lazzaretti|first2=André Eugênio|last3=Lopes|first3=Heitor Silvério|journal=Pattern Recognition Letters|volume=105|pages=13–22|bibcode=2018PaReL.105...13R}}</ref> By learning to replicate the most salient features in the training data under some of the constraints described previously, the model is encouraged to learn to precisely reproduce the most frequently observed characteristics. When facing anomalies, the model should worsen its reconstruction performance. In most cases, only data with normal instances are used to train the autoencoder; in others, the frequency of anomalies is small compared to the observation set so that its contribution to the learned representation could be ignored. After training, the autoencoder will accurately reconstruct "normal" data, while failing to do so with unfamiliar anomalous data.<ref name=":8" /> Reconstruction error (the error between the original data and its low dimensional reconstruction) is used as an anomaly score to detect anomalies.<ref name=":8" /> |
Another application for autoencoders is [[anomaly detection]].<ref name=":13" /><ref>{{Cite book |last1=Morales-Forero |first1=A. |last2=Bassetto |first2=S. |title=2019 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM) |chapter=Case Study: A Semi-Supervised Methodology for Anomaly Detection and Diagnosis |date=December 2019 |chapter-url=https://ieeexplore.ieee.org/document/8978509 |location=Macao, Macao |publisher=IEEE |pages=1031–1037 |doi=10.1109/IEEM44572.2019.8978509 |isbn=978-1-7281-3804-6|s2cid=211027131 }}</ref><ref>{{Cite book |last1=Sakurada |first1=Mayu |last2=Yairi |first2=Takehisa |title=Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis |chapter=Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction |date=December 2014 |chapter-url=http://dl.acm.org/citation.cfm?doid=2689746.2689747 |language=en |location=Gold Coast, Australia QLD, Australia |publisher=ACM Press |pages=4–11 |doi=10.1145/2689746.2689747 |isbn=978-1-4503-3159-3|s2cid=14613395 }}</ref><ref name=":8">An, J., & Cho, S. (2015). [http://dm.snu.ac.kr/static/docs/TR/SNUDM-TR-2015-03.pdf Variational Autoencoder based Anomaly Detection using Reconstruction Probability]. ''Special Lecture on IE'', ''2'', 1-18.</ref><ref>{{Cite book |last1=Zhou |first1=Chong |last2=Paffenroth |first2=Randy C. |title=Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining |chapter=Anomaly Detection with Robust Deep Autoencoders |date=2017-08-04 |chapter-url=https://dl.acm.org/doi/10.1145/3097983.3098052 |language=en |location=Halifax NS Canada |publisher=ACM |pages=665–674 |doi=10.1145/3097983.3098052 |isbn=978-1-4503-4887-4|s2cid=207557733 }}</ref><ref>{{Cite journal|doi=10.1016/j.patrec.2017.07.016|title=A study of deep convolutional auto-encoders for anomaly detection in videos|year=2018|last1=Ribeiro|first1=Manassés|last2=Lazzaretti|first2=André Eugênio|last3=Lopes|first3=Heitor Silvério|journal=Pattern Recognition Letters|volume=105|pages=13–22|bibcode=2018PaReL.105...13R}}</ref> By learning to replicate the most salient features in the training data under some of the constraints described previously, the model is encouraged to learn to precisely reproduce the most frequently observed characteristics. When facing anomalies, the model should worsen its reconstruction performance. In most cases, only data with normal instances are used to train the autoencoder; in others, the frequency of anomalies is small compared to the observation set so that its contribution to the learned representation could be ignored. After training, the autoencoder will accurately reconstruct "normal" data, while failing to do so with unfamiliar anomalous data.<ref name=":8" /> Reconstruction error (the error between the original data and its low dimensional reconstruction) is used as an anomaly score to detect anomalies.<ref name=":8" /> |
||
Recent literature has however shown that certain autoencoding models can, counterintuitively, be very good at reconstructing anomalous examples and consequently not able to reliably perform anomaly detection.<ref>{{cite arXiv|last1=Nalisnick|first1=Eric|last2=Matsukawa|first2=Akihiro|last3=Teh|first3=Yee Whye|last4=Gorur|first4=Dilan|last5=Lakshminarayanan|first5=Balaji|date=2019-02-24|title=Do Deep Generative Models Know What They Don't Know?|class=stat.ML|eprint=1810.09136}}</ref><ref>{{Cite journal|last1=Xiao|first1=Zhisheng|last2=Yan|first2=Qing|last3=Amit|first3=Yali|date=2020|title=Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder|url=https://proceedings.neurips.cc/paper/2020/hash/eddea82ad2755b24c4e168c5fc2ebd40-Abstract.html|journal=Advances in Neural Information Processing Systems|language=en|volume=33|arxiv=2003.02977}}</ref> |
Recent literature has however shown that certain autoencoding models can, counterintuitively, be very good at reconstructing anomalous examples and consequently not able to reliably perform anomaly detection.<ref>{{cite arXiv|last1=Nalisnick|first1=Eric|last2=Matsukawa|first2=Akihiro|last3=Teh|first3=Yee Whye|last4=Gorur|first4=Dilan|last5=Lakshminarayanan|first5=Balaji|date=2019-02-24|title=Do Deep Generative Models Know What They Don't Know?|class=stat.ML|eprint=1810.09136}}</ref><ref>{{Cite journal|last1=Xiao|first1=Zhisheng|last2=Yan|first2=Qing|last3=Amit|first3=Yali|date=2020|title=Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder|url=https://proceedings.neurips.cc/paper/2020/hash/eddea82ad2755b24c4e168c5fc2ebd40-Abstract.html|journal=Advances in Neural Information Processing Systems|language=en|volume=33|arxiv=2003.02977}}</ref> |
Copy and paste: – — ° ′ ″ ≈ ≠ ≤ ≥ ± − × ÷ ← → · § Cite your sources: <ref></ref>
{{}} {{{}}} | [] [[]] [[Category:]] #REDIRECT [[]] <s></s> <sup></sup> <sub></sub> <code></code> <pre></pre> <blockquote></blockquote> <ref></ref> <ref name="" /> {{Reflist}} <references /> <includeonly></includeonly> <noinclude></noinclude> {{DEFAULTSORT:}} <nowiki></nowiki> <!-- --> <span class="plainlinks"></span>
Symbols: ~ | ¡ ¿ † ‡ ↔ ↑ ↓ • ¶ # ∞ ‹› «» ¤ ₳ ฿ ₵ ¢ ₡ ₢ $ ₫ ₯ € ₠ ₣ ƒ ₴ ₭ ₤ ℳ ₥ ₦ № ₧ ₰ £ ៛ ₨ ₪ ৳ ₮ ₩ ¥ ♠ ♣ ♥ ♦ 𝄫 ♭ ♮ ♯ 𝄪 © ® ™
Latin: A a Á á À à  â Ä ä Ǎ ǎ Ă ă Ā ā à ã Å å Ą ą Æ æ Ǣ ǣ B b C c Ć ć Ċ ċ Ĉ ĉ Č č Ç ç D d Ď ď Đ đ Ḍ ḍ Ð ð E e É é È è Ė ė Ê ê Ë ë Ě ě Ĕ ĕ Ē ē Ẽ ẽ Ę ę Ẹ ẹ Ɛ ɛ Ǝ ǝ Ə ə F f G g Ġ ġ Ĝ ĝ Ğ ğ Ģ ģ H h Ĥ ĥ Ħ ħ Ḥ ḥ I i İ ı Í í Ì ì Î î Ï ï Ǐ ǐ Ĭ ĭ Ī ī Ĩ ĩ Į į Ị ị J j Ĵ ĵ K k Ķ ķ L l Ĺ ĺ Ŀ ŀ Ľ ľ Ļ ļ Ł ł Ḷ ḷ Ḹ ḹ M m Ṃ ṃ N n Ń ń Ň ň Ñ ñ Ņ ņ Ṇ ṇ Ŋ ŋ O o Ó ó Ò ò Ô ô Ö ö Ǒ ǒ Ŏ ŏ Ō ō Õ õ Ǫ ǫ Ọ ọ Ő ő Ø ø Œ œ Ɔ ɔ P p Q q R r Ŕ ŕ Ř ř Ŗ ŗ Ṛ ṛ Ṝ ṝ S s Ś ś Ŝ ŝ Š š Ş ş Ș ș Ṣ ṣ ß T t Ť ť Ţ ţ Ț ț Ṭ ṭ Þ þ U u Ú ú Ù ù Û û Ü ü Ǔ ǔ Ŭ ŭ Ū ū Ũ ũ Ů ů Ų ų Ụ ụ Ű ű Ǘ ǘ Ǜ ǜ Ǚ ǚ Ǖ ǖ V v W w Ŵ ŵ X x Y y Ý ý Ŷ ŷ Ÿ ÿ Ỹ ỹ Ȳ ȳ Z z Ź ź Ż ż Ž ž ß Ð ð Þ þ Ŋ ŋ Ə ə
Greek: Ά ά Έ έ Ή ή Ί ί Ό ό Ύ ύ Ώ ώ Α α Β β Γ γ Δ δ Ε ε Ζ ζ Η η Θ θ Ι ι Κ κ Λ λ Μ μ Ν ν Ξ ξ Ο ο Π π Ρ ρ Σ σ ς Τ τ Υ υ Φ φ Χ χ Ψ ψ Ω ω {{Polytonic|}}
Cyrillic: А а Б б В в Г г Ґ ґ Ѓ ѓ Д д Ђ ђ Е е Ё ё Є є Ж ж З з Ѕ ѕ И и І і Ї ї Й й Ј ј К к Ќ ќ Л л Љ љ М м Н н Њ њ О о П п Р р С с Т т Ћ ћ У у Ў ў Ф ф Х х Ц ц Ч ч Џ џ Ш ш Щ щ Ъ ъ Ы ы Ь ь Э э Ю ю Я я ́
IPA: t̪ d̪ ʈ ɖ ɟ ɡ ɢ ʡ ʔ ɸ β θ ð ʃ ʒ ɕ ʑ ʂ ʐ ç ʝ ɣ χ ʁ ħ ʕ ʜ ʢ ɦ ɱ ɳ ɲ ŋ ɴ ʋ ɹ ɻ ɰ ʙ ⱱ ʀ ɾ ɽ ɫ ɬ ɮ ɺ ɭ ʎ ʟ ɥ ʍ ɧ ʼ ɓ ɗ ʄ ɠ ʛ ʘ ǀ ǃ ǂ ǁ ɨ ʉ ɯ ɪ ʏ ʊ ø ɘ ɵ ɤ ə ɚ ɛ œ ɜ ɝ ɞ ʌ ɔ æ ɐ ɶ ɑ ɒ ʰ ʱ ʷ ʲ ˠ ˤ ⁿ ˡ ˈ ˌ ː ˑ ̪ {{IPA|}}
Wikidata entities used in this page
Pages transcluded onto the current version of this page (help):
This page is a member of 9 hidden categories (help):