Practical fairness achieving fair and secure data models
Fairness is an increasingly important topic as machine learning and AI more generally take over the world. While this is an active area of research, many realistic best practices are emerging at all steps along the data pipeline, from data selection and preprocessing to blackbox model audits. This b...
| Otros Autores: | |
|---|---|
| Formato: | Libro electrónico |
| Idioma: | Inglés |
| Publicado: |
Beijing :
O'Reilly
[2021]
|
| Edición: | 1st edition |
| Materias: | |
| Ver en Biblioteca Universitat Ramon Llull: | https://discovery.url.edu/permalink/34CSUC_URL/1im36ta/alma991009631290606719 |
Tabla de Contenidos:
- 1. Fairness, technology, and the real world
- 2. Understanding fairness and the data science pipeline
- 3. Fair data
- 4. Fairness pre-processing
- 5. Fairness in-processing
- 6. Fairness post-processing
- 7. Model auditing for fairness and discrimination
- 8. Interpretable models and explainability algorithms
- 9. ML models and privacy
- 10. ML models and security
- 11. Fair product design and deployment
- 12. Laws for machine learning.
