Books

Build GPT-2, Llama 3, and DeepSeek from scratch in PyTorch. Every chapter has runnable end-to-end code and loads real pretrained weights. Goes well past where most LLM tutorials stop.

Includes Editions 1, 2, 3, and 4. Editions 1-3 are listed under "Extras" after checking out, including for $0 purchases. AHSS provides a thorough intro to statistics and supports students preparing for the AP Statistics exam. B&W paperbacks (color) are sold for $25 ($40). Paperback royalties are shared between OpenIntro and the authors. Leanpub contributions go to authors to fund their time.

This book explores supervised machine learning for scientific research, addressing its limitations in interpretability, causality, and uncertainty quantification. By unifying philosophical justification with practical solutions, it provides a roadmap for turning machine learning into a rigorous tool for science.

Class imbalance isn’t a problem. Poor methodology is. This book challenges outdated practices and provides rigorous, data-driven alternatives. We focus on selecting the right tools, threshold tuning, real costs (not class frequencies), and strategic evaluation metrics, to build models that work.

This book covers R software development for building data science tools. This book provides rigorous training in the R language and covers modern software development practices for building tools that are highly reusable, modular, and suitable for use in a team-based environment or a community of developers. (Printed copies coming soon!)

The underlying goal of "Machine Learning Simplified" is to develop strong intuition into inner workings of ML. We use simple intuitive examples to explain complex concepts, algorithms or methods, as well as democratize all mathematics "behind the scenes".

This book provides a practical guide to critical data science methods, focusing on their application in credit risk management. Using examples in R and Python, it presents step-by-step processes for applying various analytical techniques while highlighting the importance of aligning methods with the specific characteristics of the data. Designed for practitioners and those with foundational data science and banking knowledge, the book bridges theory and practice with real-world examples.

Modern Computational Statistics with R teaches statistics as a disciplined way of thinking: start with the scientific question, design, data, and uncertainty before reaching for formulas. Through real examples, simulations, and R, readers learn how to turn data into defensible evidence and build the statistical foundations needed for modern data science, machine learning, and AI.

This book brings the fundamentals of R programming to you, using the same material developed as part of the industry-leading Johns Hopkins Data Science Specialization. The skills taught in this book will lay the foundation for you to begin your journey learning data science. Printed copies of this book are available through Lulu.

The essentials of making predictions using supervised regression and classification for tabular data. Tech stack: python, pandas, scikit-learn, CatBoost, LightGBM, XGBoost, TabPFN, TabICL

How should an AI system make decisions when information is incomplete?How can machines quantify uncertainty instead of merely producing predictions?How can intelligent systems continuously update their beliefs as new evidence emerges?The answer lies in Bayesian Mathematics.In Bayesian Mathematics for AI Decision Making, Anshuman Mishra explores the powerful framework that enables modern AI systems to reason probabilistically, model uncertainty, and make rational decisions in complex environments.From Bayesian inference and probabilistic programming to uncertainty-aware deep learning, reinforcement learning, healthcare diagnostics, robotics, and financial forecasting, this book reveals how Bayesian thinking is shaping the next generation of Artificial Intelligence.Learn how uncertainty becomes knowledge—and how probability becomes intelligence.

Become a better data scientist by understanding different modeling mindsets.

Artificial Intelligence is not only about neural networks and transformers. Behind many of the world's most influential AI systems lies a powerful probabilistic framework known as the Hidden Markov Model (HMM).From speech recognition and natural language processing to robotics, cybersecurity, finance, and bioinformatics, HMMs remain one of the most important sequence modeling techniques ever developed.This book takes readers on a complete journey through Markov Chains, probabilistic reasoning, Hidden Markov Models, Forward-Backward algorithms, Viterbi decoding, Baum-Welch training, and advanced HMM architectures.Designed for students, researchers, and AI professionals, the book combines rigorous mathematics with practical applications, making complex concepts accessible and immediately useful.If you want to truly understand how intelligent systems model uncertainty, learn from temporal patterns, and reason about hidden information, this book provides the foundation.