Books

A clear, illustrated guide to large language models, covering key concepts and practical applications. Ideal for projects, interviews, or personal learning.

Skip the black-box frameworks. Build a production-grade AI coding agent from scratch in pure Python - cloud or local, tested with pytest, all in a single file.

Everything you really need to know in Machine Learning in a hundred pages.

Revised for PyTorch 2.x! In 2019, I published a PyTorch tutorial on Towards Data Science and I was amazed by the reaction from the readers! Their feedback motivated me to write this book to help beginners start their journey into Deep Learning and PyTorch. I hope you enjoy reading this book as much as I enjoy writing it.

800 pages. 11 chapters. The full forecasting stack in Python — from ARIMA to foundation models — with production-grade code and proper evaluation. No hype.

A powerful new book on Conformal Prediction by bestselling author and machine learning expert Valery Manokhin, bridging theory and real-world machine learning. Discover how to quantify uncertainty with statistical guarantees—across deep learning, time series, forecasting, and more. Preorder now before the price goes up.

Build a complete LLM inference engine in C++ — from a blankproject to a working Transformer that loads a real model andgenerates text. Forged one challenge at a time, with teststhat prove every piece works before you move on.

Learn Next.js by building a real AI-powered application, from project setup to production deployment. This book covers the complete journey: TypeScript, React, Next.js App Router, Prisma, authentication, the Vercel AI SDK (chat, RAG, tool calling), testing, security, and deployment. One project, 29 chapters, no toy demos.

It's never been easier to build an AI agent — and never been harder to make one that actually works. This book takes you from language model foundations to production-ready multi-agent systems with the depth to predict failure before it happens, engineer graceful degradation over catastrophic failure, and take absolute architectural ownership. Get the paperback from amazon.

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.

Pull a model onto a machine you own, shape it with a Modelfile, fine-tune your own adapter, and build a chat app that calls tools and talks to an MCP server, all running on your own hardware. By the end, you'll know exactly where owning your AI beats renting it, and where it doesn't.

Anyone can run INT4 and read off the accuracy drop. This book explains why that number is what it is — building every quantization method from scratch, breaking it on purpose, and measuring the result. Quantization, from the bits up.

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.

Stop guessing which machine learning algorithm to use. This book provides clear mathematical explanations, decision frameworks, and real-world examples to help you select, implement, and evaluate models correctly from data to deployment.