Building Responsible AI Algorithms : A Framework for Transparency, Fairness, Safety, Privacy, and Robustness / / by Toju Duke
| Building Responsible AI Algorithms : A Framework for Transparency, Fairness, Safety, Privacy, and Robustness / / by Toju Duke |
| Autore | Duke Toju |
| Edizione | [1st ed. 2023.] |
| Pubbl/distr/stampa | Berkeley, CA : , : Apress : , : Imprint : Apress, , 2023 |
| Descrizione fisica | 1 online resource (196 pages) |
| Disciplina | 006.3 |
| Soggetto topico |
Machine learning
Technology - Moral and ethical aspects Artificial intelligence Machine Learning Ethics of Technology Artificial Intelligence |
| ISBN |
9781484293065
1484293061 |
| Formato | Materiale a stampa |
| Livello bibliografico | Monografia |
| Lingua di pubblicazione | eng |
| Nota di contenuto | Part I. Foundation -- 1. Responsibility -- 2. AI Principles -- 3. Data -- Part II. Implementation -- 4. Fairness -- 5. Safety -- 6. Humans in the Loop -- 7. Explainability -- 8. Privacy -- 9. Robustness -- Part III. Ethical Considerations -- 10. Ethics of AI and ML -- Appendix A: References. |
| Record Nr. | UNINA-9910741137403321 |
Duke Toju
|
||
| Berkeley, CA : , : Apress : , : Imprint : Apress, , 2023 | ||
| Lo trovi qui: Univ. Federico II | ||
| ||
Responsible AI in Practice : A Practical Guide to Safe and Human AI / / by Toju Duke, Paolo Giudici
| Responsible AI in Practice : A Practical Guide to Safe and Human AI / / by Toju Duke, Paolo Giudici |
| Autore | Duke Toju |
| Edizione | [1st ed. 2025.] |
| Pubbl/distr/stampa | Berkeley, CA : , : Apress : , : Imprint : Apress, , 2025 |
| Descrizione fisica | 1 online resource (171 pages) |
| Disciplina | 006.3 |
| Altri autori (Persone) | GiudiciPaolo |
| Soggetto topico |
Artificial intelligence
Artificial intelligence - Moral and ethical aspects Risk assessment |
| ISBN | 9798868811661 |
| Formato | Materiale a stampa |
| Livello bibliografico | Monografia |
| Lingua di pubblicazione | eng |
| Nota di contenuto | Part I: Introduction -- Chapter 1: Responsible AI and AI Governance -- Part II: Technical risks (Internal to an organisation) -- Chapter 2. Accuracy -- Chapter 3. Robustness and Security -- Chapter 4: Explainability -- Part III: Ethical risks (External) -- Chapter 5. Fairness and Human Rights -- Chapter 6: Privacy -- Chapter 7: Sustainability -- Chapter 8: Human-Centered AI -- Part IV: Governance and Case studies -- Chapter 9: Governance Processes -- Chapters 10: Case Study. |
| Record Nr. | UNINA-9910983301003321 |
Duke Toju
|
||
| Berkeley, CA : , : Apress : , : Imprint : Apress, , 2025 | ||
| Lo trovi qui: Univ. Federico II | ||
| ||