Conformal Prediction
A Gentle Introduction
Seiten
2023
now publishers Inc (Verlag)
978-1-63828-158-0 (ISBN)
now publishers Inc (Verlag)
978-1-63828-158-0 (ISBN)
In this hands-on introduction the authors provide the reader with a working understanding of conformal prediction and related distribution-free uncertainty quantification techniques. They lead the reader through practical theory and examples of conformal prediction and describe its extensions to complex machine learning tasks.
Black-box machine learning models are now routinely used in high-risk settings, like medical diagnostics, which demand uncertainty quantification to avoid consequential model failures. Conformal prediction is a user-friendly paradigm for creating statistically rigorous uncertainty sets/intervals for the predictions of such models. One can use conformal prediction with any pre-trained model, such as a neural network, to produce sets that are guaranteed to contain the ground truth with a user-specified probability, such as 90%. It is easy-to-understand, easy-to-use, and in general, applies naturally to problems arising in the fields of computer vision, natural language processing, deep reinforcement learning, amongst others.
In this hands-on introduction the authors provide the reader with a working understanding of conformal prediction and related distribution-free uncertainty quantification techniques. They lead the reader through practical theory and examples of conformal prediction and describe its extensions to complex machine learning tasks involving structured outputs, distribution shift, time-series, outliers, models that abstain, and more. Throughout, there are many explanatory illustrations, examples, and code samples in Python. With each code sample comes a Jupyter notebook implementing the method on a real-data example.
This hands-on tutorial, full of practical and accessible examples, is essential reading for all students, practitioners and researchers working on all types of systems deploying machine learning techniques.
Black-box machine learning models are now routinely used in high-risk settings, like medical diagnostics, which demand uncertainty quantification to avoid consequential model failures. Conformal prediction is a user-friendly paradigm for creating statistically rigorous uncertainty sets/intervals for the predictions of such models. One can use conformal prediction with any pre-trained model, such as a neural network, to produce sets that are guaranteed to contain the ground truth with a user-specified probability, such as 90%. It is easy-to-understand, easy-to-use, and in general, applies naturally to problems arising in the fields of computer vision, natural language processing, deep reinforcement learning, amongst others.
In this hands-on introduction the authors provide the reader with a working understanding of conformal prediction and related distribution-free uncertainty quantification techniques. They lead the reader through practical theory and examples of conformal prediction and describe its extensions to complex machine learning tasks involving structured outputs, distribution shift, time-series, outliers, models that abstain, and more. Throughout, there are many explanatory illustrations, examples, and code samples in Python. With each code sample comes a Jupyter notebook implementing the method on a real-data example.
This hands-on tutorial, full of practical and accessible examples, is essential reading for all students, practitioners and researchers working on all types of systems deploying machine learning techniques.
1. Conformal Prediction
2. Examples of Conformal Procedures
3. Evaluating Conformal Prediction
4. Extensions of Conformal Prediction
5. Worked Examples
6. Full Conformal Prediction
7. Historical Notes on Conformal Prediction
8. Acknowledgements
Appendices
References
Erscheinungsdatum | 03.04.2023 |
---|---|
Reihe/Serie | Foundations and Trends® in Machine Learning |
Verlagsort | Hanover |
Sprache | englisch |
Maße | 156 x 234 mm |
Gewicht | 173 g |
Themenwelt | Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik |
ISBN-10 | 1-63828-158-0 / 1638281580 |
ISBN-13 | 978-1-63828-158-0 / 9781638281580 |
Zustand | Neuware |
Haben Sie eine Frage zum Produkt? |
Mehr entdecken
aus dem Bereich
aus dem Bereich
was sie kann & was uns erwartet
Buch | Softcover (2023)
C.H.Beck (Verlag)
18,00 €
von absurd bis tödlich: Die Tücken der künstlichen Intelligenz
Buch | Softcover (2023)
Heyne (Verlag)
20,00 €
dem Menschen überlegen – wie KI uns rettet und bedroht
Buch | Hardcover (2023)
Droemer (Verlag)
24,00 €