Books

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

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.

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.

PyTorch Deep Dive is a practical guide to mastering modern deep learning with PyTorch. From core concepts to advanced topics like transformers, diffusion models, and production deployment, it combines clear explanations, hands-on examples, and real-world best practices to help you build and scale AI applications with confidence.

Понятный иллюстрированный путеводитель по ключевым концепциям и практическим применениям больших языковых моделей. Идеально подходит для работы над проектами, подготовки к собеседованиям и самостоятельного обучения.

Most people think they are bad at math. In reality, they were never taught arithmetic properly.This book is a modern English edition of Arithmetic by Alexander P. Kiselev—the text that formed the backbone of mathematical education in Russia and USSR for over a century and helped produce generations of exceptionally strong mathematicians, scientists, and engineers.Unlike modern textbooks that prioritise shortcuts, visuals, and lowered expectations, Kiselev builds arithmetic logically, systematically, and rigorously. Every method is explained. Every operation has meaning. Exercises are carefully sequenced to develop real understanding—not rote pattern-following.This book does not promise “easy math”. It promises something better: clarity, confidence, and competence.Whether you are a student, a parent, a tutor, or an adult rebuilding fundamentals, this book will change how you understand arithmetic—and why so much later mathematics suddenly becomes easier.

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.

A practical guide to fine-tuning Large Language Models (LLMs), offering both a high-level overview and detailed instructions on how to train these models for specific tasks.Get the paperback version here. Get the Kindle version here.

Keyword search misses meaning. Vector search misses precision. This book shows you how to combine them into production systems that deliver both, with architecture patterns, model selection frameworks, evaluation methodology, and operational guidance grounded in primary research.

Most AI systems fail in production. They chain prompts together and call it "agentic". They collapse under real-world pressure. The gap isn't the technology – it's missing infrastructure. This book bridges that gap. Learn the architecture patterns and infrastructure to build autonomous AI systems that work at scale. Master what distinguishes real agents from chatbots with tools. Deploy with confidence. Stop building demos. Start shipping production agentic AI.

大規模言語モデル (LLM) の主要な概念から実践的な応用例まで、簡潔に図解されている学習ガイドです。プロジェクトでの利用、面接対策、個人的な学習にも最適です。

Go beyond calling transformer libraries and learn what actually happens under the hood. Starting from first principles, this book builds transformers from scratch with NumPy and PyTorch, then takes you through training, optimization and production inference. Along the way, you’ll work through the math, code and practical techniques behind modern transformer systems.

Master machine learning interpretability with this comprehensive guide to SHAP – your tool to communicating model insights and building trust in all your machine learning applications.

Learn how to implement various feature selection methods in a few lines of code and train faster, simpler, and more reliable machine learning models. Using Python open-source libraries, you will learn how to find the most predictive features from your data through filter, wrapper, embedded, and additional feature selection methods.