by Michael Munn
First published 2022
Most machine learning practitioners know how to build accurate models, but they struggle to understand what drives their algorithms' decisions. When prediction accuracy becomes the sole focus, the reasoning behind those predictions remains hidden. This practical guide shifts attention from optimization metrics to model transparency. Machine learning engineers and data scientists learn to apply explainability techniques that reveal how their models actually work. The book combines hands-on methods with real-world applications, showing practitioners how to integrate these tools into their existing workflows. Rather than treating explainability as an afterthought, readers discover how understanding model behavior becomes central to building reliable systems.
Genres: science, non-fiction, 21st-century, artificial-intelligence, computer-science, academic, algorithms
Vibes: thought-provoking
Tropes: how-to
276 pages · Paperback · O'Reilly Media