Interpretable AI

• Verfasst von: Thampi, Ajay [VerfasserIn]
• Titel: Interpretable AI
• Verf.angabe: Ajay Thampi
• Ausgabe: [First edition].
• Verlagsort: [Shelter Island, New York]
• Verlag: Manning Publications
• E-Jahr: 2022
• Jahr: [2022]
• Umfang: 1 online resource (1 sound file (8 hr., 39 min.))
• Fussnoten: Online resource; title from title details screen (O’Reilly, viewed May 21, 2024)
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Apprentissage automatique
• Sach-SW: Intelligence artificielle
• Sach-SW: Python (Langage de programmation)
• Sach-SW: artificial intelligence
• Sach-SW: Audiobooks
• Sach-SW: Livres audio
• K10plus-PPN: 1890486191
• K10plus-PPN:
  Universitätsbibliothek
• Lokale URL UB: Zum Volltext
• Lokale URL UB: Bibliothek der Medizinischen Fakultät Mannheim der Universität Heidelberg
• Bibliothek/Idn: UW / m4533729452
• Lokale URL Inst.: Zum Volltext

Abstract

Interpretable AI teaches you to identify the patterns your model has learned and why it produces its results. As you read, you’ll pick up algorithm-specific approaches, like interpreting regression and generalized additive models, along with tips to improve performance during training. You’ll also explore methods for interpreting complex deep learning models where some processes are not easily observable. AI transparency is a fast-moving field, and this book simplifies cutting-edge research into practical methods you can implement with Python.