Books

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

Master language models through mathematics, illustrations, and code―and build your own from scratch!

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.

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.

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.

This book is a quick foray into the world of deep learning-based computer vision and abnormal equipment sound detection. The readers are introduced to the ease with which powerful equipment and product quality monitoring solutions can be built using sound and visual data.

From quantum and molecules to cells, individuals, organizations, nations, and civilizations—why do clearly defined hierarchical structures emerge? Why does evolution often manifest as a repeating rhythm of "oscillation—stability—aggregation—re-stability"? Why do many systems fail not because of insufficient power or lack of information, but because the "pace of doing things" is wrong?

Build a world-class technical publishing brand with this complete guide to designing, structuring, and publishing professional Tech Capsules. Learn proven layouts, visual identity, content architecture, publishing workflows, and best practices used to create high-quality technical micro-books that readers lov

Every news feed is full of AI buzzwords: Transformers, tokens, embeddings, context windows, hallucinations, objective functions. Yet most explanations are either dense academic textbooks or empty marketing fluff. ☕ Coffee Break AI is your practical guide to AI. Written in plain English with warm real-world analogies. It breaks down the core mechanisms of AI into 40 bite-sized chapters.

We'll stick to five libraries, not because more would be a problem, but because keeping it simple shows how well we can organise things. When you download MNIST with just the standard library, you finally see what a dataset loader was hiding. If you write attention as four lines of NumPy before you ever call a PyTorch module, it's no longer a magic process but just plain arithmetic.

Deep learning is transforming the world, and this book provides a clear, practical path to mastering it. Through concise explanations and hands-on Python examples, you will learn to build, train, optimize, and deploy neural networks with confidence for real-world applications.

Make your Python AI code up to 100× faster using NumPy vectorization, Numba, parallel execution, and GPU acceleration. Learn through practical benchmarks and real-world optimization examples.

Move beyond the API. Dismantle the AI black box and build generative engines from scratch with pure Python and NumPy. Master the profound geometric principles and applied mathematics driving LLMs and Transformers. Transform from a mere consumer into an elite AI innovator by writing the core mathematical architecture yourself—no shortcuts, no frameworks, just pure engineering excellence.

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.