Signatures to help interpretability of anomalies
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908414588747776 |
|---|---|
| author | Gangler, Emmanuel Ishida, Emille E. O. Kornilov, Matwey V. Korolev, Vladimir Lavrukhina, Anastasia Malanchev, Konstantin Pruzhinskaya, Maria V. Russeil, Etienne Semenikhin, Timofey Sreejith, Sreevarsha Volnova, Alina A. |
| author_facet | Gangler, Emmanuel Ishida, Emille E. O. Kornilov, Matwey V. Korolev, Vladimir Lavrukhina, Anastasia Malanchev, Konstantin Pruzhinskaya, Maria V. Russeil, Etienne Semenikhin, Timofey Sreejith, Sreevarsha Volnova, Alina A. |
| contents | Machine learning is often viewed as a black box when it comes to understanding its output, be it a decision or a score. Automatic anomaly detection is no exception to this rule, and quite often the astronomer is left to independently analyze the data in order to understand why a given event is tagged as an anomaly. We introduce here idea of anomaly signature, whose aim is to help the interpretability of anomalies by highlighting which features contributed to the decision. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_16314 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Signatures to help interpretability of anomalies Gangler, Emmanuel Ishida, Emille E. O. Kornilov, Matwey V. Korolev, Vladimir Lavrukhina, Anastasia Malanchev, Konstantin Pruzhinskaya, Maria V. Russeil, Etienne Semenikhin, Timofey Sreejith, Sreevarsha Volnova, Alina A. Machine Learning Instrumentation and Methods for Astrophysics Machine learning is often viewed as a black box when it comes to understanding its output, be it a decision or a score. Automatic anomaly detection is no exception to this rule, and quite often the astronomer is left to independently analyze the data in order to understand why a given event is tagged as an anomaly. We introduce here idea of anomaly signature, whose aim is to help the interpretability of anomalies by highlighting which features contributed to the decision. |
| title | Signatures to help interpretability of anomalies |
| topic | Machine Learning Instrumentation and Methods for Astrophysics |
| url | https://arxiv.org/abs/2506.16314 |