Pages
160
Year
2019
Level
beginner to intermediate
Read time
4h
Andriy Burkov · Andriy Burkov (self-published) · 2019
Reviewed by Ashish Sheth · Updated April 2026
The Hundred-Page Machine Learning Book
4.6 / 5
AMAZON · 1.4K RATINGS
machine learning
SUBJECTS
What you'll come away with
01.
A complete vocabulary of ML algorithms and when to use each
02.
How model evaluation and bias-variance tradeoff actually work
03.
Why feature engineering matters more than algorithm choice for most problems
04.
Practical guidance on hyperparameter tuning and regularization
05.
Mental models for thinking about ML problems systematically
06.
What to study next, organized by topic
Strengths
+Distills a massive field into ~150 readable pages
+Endorsed by Peter Norvig and other ML luminaries
+Author follows up with companion books for deeper dives
+Costs less than a textbook chapter and is more useful
Caveats
−Genuinely a survey, not a tutorial — you cannot build models from this alone
−Some math notation moves fast for absolute beginners
−Not enough depth to prepare for ML engineer interviews at top companies
★ 4.6 FROM 1.4K READERS ON AMAZON
Check Price on Amazon →
Read this if
→Software engineers who want a map of ML before committing to a 900-page tome
→Engineering managers who need to evaluate ML proposals from their teams
→Anyone who keeps forgetting what 'cross-validation' or 'L2 regularization' means
Skip this if
—Beginners who learn by typing code, not reading concepts
—Engineers preparing for hands-on ML interviews (read Hands-On Machine Learning instead)
—Researchers wanting derivations and proofs
Head-to-head comparisons
The Hundred-Page Machine Learning Book vs Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow → The Hundred-Page Machine Learning Book vs Designing Machine Learning Systems → The Hundred-Page Machine Learning Book vs Deep Learning with Python → The Hundred-Page Machine Learning Book vs Co-Intelligence → Frequently asked
Can I really learn machine learning in 100 pages?
You can learn the vocabulary, the major algorithms, and how to think about ML problems. You cannot learn to build production models. Treat this as a map, not a tutorial.
Should I read this before or after Hands-On Machine Learning?
Read Burkov first if you want the lay of the land before committing to a long book. Read Hands-On ML if you prefer to learn by building. They complement each other.
Is this still relevant in 2026?
The 2019 publication date matters less than you'd think. Burkov covers fundamentals that haven't changed. For LLM-era content, pair it with the author's newer Hundred-Page Language Models Book.
Read this next
3 alternatives
Ready?
Check Price on Amazon →