Machine Learning

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.

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.

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

Unlock the full potential of CatBoost — a powerful gradient boosting library built for structured/tabular data and still underused in practice.In Mastering CatBoost: The Hidden Gem of Tabular AI, you’ll learn how to take advantage of CatBoost’s key strengths: native categorical feature handling, strong accuracy, and fast inference — without brittle preprocessing pipelines.Written for data scientists, ML engineers, and applied researchers, the book covers:Real-world use cases and end-to-end workflowsPractical tuning strategies and diagnosticsInterpretability with SHAP, feature importance, and constraintsDeployment-minded best practices and common failure modesWhether you’re new to CatBoost or ready to go deeper, this is a clear, practical guide to building high-performance tabular models.Early Access is available now, with ongoing updates leading to the full release in 2026.

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 model that wins on MAPE can lose money on the shelf. A 15% accuracy gain can hide a 12% bias. An interval that looks tight can be wrong a third of the time.Forecast metrics are decision instruments, not neutral truth detectors — and most teams are still choosing them by habit. This book shows where MAE, MAPE, sMAPE, WAPE, MASE, RMSSE, CRPS, pinball loss, energy scores, bias measures and cost-based metrics help, and where they quietly mislead.Twelve chapters take you from elicitation and baselines through intermittent demand, probabilistic and hierarchical scoring, and the accuracy–utility gap, to a production evaluation system with monitoring, drift detection, alerting and governance. Every metric arrives with its assumptions, every criticism carries a remedy, and a retrospective Walmart M5 case study runs throughout, with Python listings and reproducibility checks.For demand planners, forecasting data scientists, ML engineers and analytics leads who need evaluation choices they can defend. Measure what matters.

"If you intend to use machine learning to solve business problems at scale, I'm delighted you got your hands on this book." —Cassie Kozyrkov, Chief Decision Scientist at Google "Foundational work about the reality of building machine learning models in production." —Karolis Urbonas, Head of Machine Learning and Science at Amazon

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.

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 approach to Prompt Engineering for developers. Dive into the world of Prompt Engineering agility, optimizing your prompts for dynamic LLM interactions. Learn with hands-on examples from the real world and elevate your developer experience with LLMs. Discover how the right prompts can revolutionize your interactions with LLMs.

The latest version of Rust (1.85) has some great new features, like async closures, more stable associated function return types, and const generics that are now mature enough to underpin serious numerical libraries. The linfa and smartcore ecosystems have developed into decent classical machine learning stacks. The Burn training framework feels native to Rust, not like it's been ported from it. The Candle makes it so that loading pre-trained transformer models is more of an engineering task than a research exercise. The crates that used to need all sorts of workarounds now just work.

This book is meant to discover how the language Rust, which is known for being fast and safe, can work with the constantly changing field of machine learning, neural networks and deep learning. The datasets of COVID, CIFAR-10 and practical examples are meant to show how Rust's features can be used to solve problems that come up in machine learning.

Transform your software creation process with AI Driven Development (AIDD). Learn to harness AI to generate programs, unlocking 10x - 20x productivity gains while building components, tests, and documentation. Written for software engineers, product managers, code conjurers and aspiring tinkerers, this book teaches you to express complex functional requirements using natural language with the precision of code, utilizing SudoLang - a language designed specifically for communicating ideas to AI language models. You'll learn to streamline your workflow, reduce code complexity, and craft more intelligent, responsive applications that adapt to user needs.Design and implement AI-powered applications using SudoLang, and any common programming language or framework. Examples will use JavaScript, Next.js, and React.