PiShield: A PyTorch Package for Learning with Requirements
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_ | 1866929343152783360 |
|---|---|
| author | Stoian, Mihaela Cătălina Tatomir, Alex Lukasiewicz, Thomas Giunchiglia, Eleonora |
| author_facet | Stoian, Mihaela Cătălina Tatomir, Alex Lukasiewicz, Thomas Giunchiglia, Eleonora |
| contents | Deep learning models have shown their strengths in various application domains, however, they often struggle to meet safety requirements for their outputs. In this paper, we introduce PiShield, the first package ever allowing for the integration of the requirements into the neural networks' topology. PiShield guarantees compliance with these requirements, regardless of input. Additionally, it allows for integrating requirements both at inference and/or training time, depending on the practitioners' needs. Given the widespread application of deep learning, there is a growing need for frameworks allowing for the integration of the requirements across various domains. Here, we explore three application scenarios: functional genomics, autonomous driving, and tabular data generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_18285 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PiShield: A PyTorch Package for Learning with Requirements Stoian, Mihaela Cătălina Tatomir, Alex Lukasiewicz, Thomas Giunchiglia, Eleonora Machine Learning Artificial Intelligence Logic in Computer Science Deep learning models have shown their strengths in various application domains, however, they often struggle to meet safety requirements for their outputs. In this paper, we introduce PiShield, the first package ever allowing for the integration of the requirements into the neural networks' topology. PiShield guarantees compliance with these requirements, regardless of input. Additionally, it allows for integrating requirements both at inference and/or training time, depending on the practitioners' needs. Given the widespread application of deep learning, there is a growing need for frameworks allowing for the integration of the requirements across various domains. Here, we explore three application scenarios: functional genomics, autonomous driving, and tabular data generation. |
| title | PiShield: A PyTorch Package for Learning with Requirements |
| topic | Machine Learning Artificial Intelligence Logic in Computer Science |
| url | https://arxiv.org/abs/2402.18285 |