Knowledge-Augmented Explainable and Interpretable Learning for Anomaly Detection and Diagnosis
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909410230534144 |
|---|---|
| author | Atzmueller, Martin Bohne, Tim Windler, Patricia |
| author_facet | Atzmueller, Martin Bohne, Tim Windler, Patricia |
| contents | Knowledge-augmented learning enables the combination of knowledge-based and data-driven approaches. For anomaly detection and diagnosis, understandability is typically an important factor, especially in high-risk areas. Therefore, explainability and interpretability are also major criteria in such contexts. This chapter focuses on knowledge-augmented explainable and interpretable learning to enhance understandability, transparency and ultimately computational sensemaking. We exemplify different approaches and methods in the domains of anomaly detection and diagnosis - from comparatively simple interpretable methods towards more advanced neuro-symbolic approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_00146 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Knowledge-Augmented Explainable and Interpretable Learning for Anomaly Detection and Diagnosis Atzmueller, Martin Bohne, Tim Windler, Patricia Machine Learning Artificial Intelligence Knowledge-augmented learning enables the combination of knowledge-based and data-driven approaches. For anomaly detection and diagnosis, understandability is typically an important factor, especially in high-risk areas. Therefore, explainability and interpretability are also major criteria in such contexts. This chapter focuses on knowledge-augmented explainable and interpretable learning to enhance understandability, transparency and ultimately computational sensemaking. We exemplify different approaches and methods in the domains of anomaly detection and diagnosis - from comparatively simple interpretable methods towards more advanced neuro-symbolic approaches. |
| title | Knowledge-Augmented Explainable and Interpretable Learning for Anomaly Detection and Diagnosis |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2412.00146 |