Predictable Artificial Intelligence
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916554026778624 |
|---|---|
| author | Zhou, Lexin Moreno-Casares, Pablo A. Martínez-Plumed, Fernando Burden, John Burnell, Ryan Cheke, Lucy Ferri, Cèsar Marcoci, Alexandru Mehrbakhsh, Behzad Moros-Daval, Yael hÉigeartaigh, Seán Ó Rutar, Danaja Schellaert, Wout Voudouris, Konstantinos Hernández-Orallo, José |
| author_facet | Zhou, Lexin Moreno-Casares, Pablo A. Martínez-Plumed, Fernando Burden, John Burnell, Ryan Cheke, Lucy Ferri, Cèsar Marcoci, Alexandru Mehrbakhsh, Behzad Moros-Daval, Yael hÉigeartaigh, Seán Ó Rutar, Danaja Schellaert, Wout Voudouris, Konstantinos Hernández-Orallo, José |
| contents | We introduce the fundamental ideas and challenges of Predictable AI, a nascent research area that explores the ways in which we can anticipate key validity indicators (e.g., performance, safety) of present and future AI ecosystems. We argue that achieving predictability is crucial for fostering trust, liability, control, alignment and safety of AI ecosystems, and thus should be prioritised over performance. We formally characterise predictability, explore its most relevant components, illustrate what can be predicted, describe alternative candidates for predictors, as well as the trade-offs between maximising validity and predictability. To illustrate these concepts, we bring an array of illustrative examples covering diverse ecosystem configurations. Predictable AI is related to other areas of technical and non-technical AI research, but have distinctive questions, hypotheses, techniques and challenges. This paper aims to elucidate them, calls for identifying paths towards a landscape of predictably valid AI systems and outlines the potential impact of this emergent field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_06167 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Predictable Artificial Intelligence Zhou, Lexin Moreno-Casares, Pablo A. Martínez-Plumed, Fernando Burden, John Burnell, Ryan Cheke, Lucy Ferri, Cèsar Marcoci, Alexandru Mehrbakhsh, Behzad Moros-Daval, Yael hÉigeartaigh, Seán Ó Rutar, Danaja Schellaert, Wout Voudouris, Konstantinos Hernández-Orallo, José Artificial Intelligence I.2 We introduce the fundamental ideas and challenges of Predictable AI, a nascent research area that explores the ways in which we can anticipate key validity indicators (e.g., performance, safety) of present and future AI ecosystems. We argue that achieving predictability is crucial for fostering trust, liability, control, alignment and safety of AI ecosystems, and thus should be prioritised over performance. We formally characterise predictability, explore its most relevant components, illustrate what can be predicted, describe alternative candidates for predictors, as well as the trade-offs between maximising validity and predictability. To illustrate these concepts, we bring an array of illustrative examples covering diverse ecosystem configurations. Predictable AI is related to other areas of technical and non-technical AI research, but have distinctive questions, hypotheses, techniques and challenges. This paper aims to elucidate them, calls for identifying paths towards a landscape of predictably valid AI systems and outlines the potential impact of this emergent field. |
| title | Predictable Artificial Intelligence |
| topic | Artificial Intelligence I.2 |
| url | https://arxiv.org/abs/2310.06167 |