Book - Machine Learning Beyond Point Predictions: Uncertainty Quantification
Author: Rafael Izbicki
1st Edition, 2025
ISBN: 978-65-01-20272-3
Pages: 260
Language: English
❗ If you live in Brazil, access the Brazilian version of the webpage by clicking here.
Where to Buy
📘 You can buy a printed version from Amazon or search in your local store.
Download the Book
📥 Download the full book in PDF format for free: Click here.
About the Book
This book offers a comprehensive and practical introduction to uncertainty quantification in supervised machine learning. It is written for researchers and practitioners with a good mathematical background and includes applications in fields such as cosmology and infectious disease forecasting.
Topics include:
- Conditional density estimation with mixtures and neural networks
- Gaussian Processes and Bayesian Additive Regression Trees
- Conformal prediction and calibration methods
- Uncertainty decomposition (aleatoric and epistemic)
- Likelihood-free inference and simulation-based inference
Hands-on examples and code are available in the accompanying GitHub repository.
How to Cite
📚 Izbicki, R. Machine Learning Beyond Point Predictions: Uncertainty Quantification. 1st edition, 2025, 260 pages. ISBN: 978-65-01-20272-3.
📜 BibTeX entry: click here.
Code and Examples
🛠️ Github with code: https://github.com/rizbicki/UQ4ML/