Cargando…
An introduction to machine learning interpretability : an applied perspective on fairness, accountability, transparency, and explainable AI /
Innovation and competition are driving analysts and data scientists toward increasingly complex predictive modeling and machine learning algorithms. This complexity makes these models accurate, but can also make their predictions difficult to understand. When accuracy outpaces interpretability, huma...
| Clasificación: | Libro Electrónico |
|---|---|
| Autores principales: | , |
| Formato: | Electrónico eBook |
| Idioma: | Inglés |
| Publicado: |
Sebastopol, CA :
O'Reilly Media,
[2019]
|
| Edición: | Second edition. |
| Temas: | |
| Acceso en línea: | Texto completo (Requiere registro previo con correo institucional) |
MARC
| LEADER | 00000cam a2200000 i 4500 | ||
|---|---|---|---|
| 001 | OR_on1127579464 | ||
| 003 | OCoLC | ||
| 005 | 20231017213018.0 | ||
| 006 | m o d | ||
| 007 | cr unu|||||||| | ||
| 008 | 191114s2019 caua ob 000 0 eng d | ||
| 040 | |a UMI |b eng |e rda |e pn |c UMI |d OCLCF |d CZL |d OCLCQ |d OCLCO |d OCLCQ |d OCLCO | ||
| 020 | |z 9781098115470 | ||
| 035 | |a (OCoLC)1127579464 | ||
| 037 | |a CL0501000082 |b Safari Books Online | ||
| 050 | 4 | |a Q325.5 | |
| 049 | |a UAMI | ||
| 100 | 1 | |a Hall, Patrick, |e author. | |
| 245 | 1 | 3 | |a An introduction to machine learning interpretability : |b an applied perspective on fairness, accountability, transparency, and explainable AI / |c Patrick Hall and Navdeep Gill. |
| 246 | 3 | 0 | |a Applied perspective on fairness, accountability, transparency, and explainable AI |
| 250 | |a Second edition. | ||
| 264 | 1 | |a Sebastopol, CA : |b O'Reilly Media, |c [2019] | |
| 264 | 4 | |c Ã2019 | |
| 300 | |a 1 online resource (1 volume) : |b illustrations | ||
| 336 | |a text |b txt |2 rdacontent | ||
| 337 | |a computer |b c |2 rdamedia | ||
| 338 | |a online resource |b cr |2 rdacarrier | ||
| 504 | |a Includes bibliographical references. | ||
| 588 | 0 | |a Online resource; title from title page (viewed November 12, 2019). | |
| 520 | |a Innovation and competition are driving analysts and data scientists toward increasingly complex predictive modeling and machine learning algorithms. This complexity makes these models accurate, but can also make their predictions difficult to understand. When accuracy outpaces interpretability, human trust suffers, affecting business adoption, model validation efforts, and regulatory oversight. In the updated edition of this ebook, Patrick Hall and Navdeep Gill from H2O.ai introduce the idea of machine learning interpretability and examine a set of machine learning techniques, algorithms, and models to help data scientists improve the accuracy of their predictive models while maintaining a high degree of interpretability. While some industries require model transparency, such as banking, insurance, and healthcare, machine learning practitioners in almost any vertical will likely benefit from incorporating the discussed interpretable models, and debugging, explanation, and fairness approaches into their workflow. This second edition discusses new, exact model explanation techniques, and de-emphasizes the trade-off between accuracy and interpretability. This edition also includes up-to-date information on cutting-edge interpretability techniques and new figures to illustrate the concepts of trust and understanding in machine learning models. Learn how machine learning and predictive modeling are applied in practice Understand social and commercial motivations for machine learning interpretability, fairness, accountability, and transparency Get a definition of interpretability and learn about the groups leading interpretability research Examine a taxonomy for classifying and describing interpretable machine learning approaches Gain familiarity with new and more traditional interpretable modeling approaches See numerous techniques for understanding and explaining models and predictions Read about methods to debug prediction errors, sociological bias, and security vulnerabilities in predictive models Get a feel for the techniques in action with code examples. | ||
| 590 | |a O'Reilly |b O'Reilly Online Learning: Academic/Public Library Edition | ||
| 650 | 0 | |a Machine learning. | |
| 650 | 0 | |a Artificial intelligence. | |
| 650 | 2 | |a Artificial Intelligence | |
| 650 | 2 | |a Machine Learning | |
| 650 | 6 | |a Apprentissage automatique. | |
| 650 | 6 | |a Intelligence artificielle. | |
| 650 | 7 | |a artificial intelligence. |2 aat | |
| 650 | 7 | |a Artificial intelligence |2 fast | |
| 650 | 7 | |a Machine learning |2 fast | |
| 700 | 1 | |a Gill, Navdeep, |e author. | |
| 856 | 4 | 0 | |u https://learning.oreilly.com/library/view/~/9781098115487/?ar |z Texto completo (Requiere registro previo con correo institucional) |
| 994 | |a 92 |b IZTAP | ||