New to Artificial Intelligence? Read the Artificial Intelligence article
Stop guessing prompts. Start from the result you want.Why does AI give you generic answers? Because you start from the wrong end.A prompt that works the first time is not luck. It is a method.
Build practical AI agents and automate real-world digital workflows through five hands-on projects. Learn to create research, email, social media, news digest, and code review agents using modern AI tools and step-by-step implementation guidance.
Build real-world web applications with the power of AI!Learn to create five practical full-stack projects—from a professional portfolio and SaaS landing page to an e-commerce catalogue and real-time chat application.Explore modern web technologies, AI-assisted coding, database integration, testing, debugging, and deployment through a hands-on learning approach.Plan. Build. Test. Deploy. Learn modern web development with AI assistance.
What happens when artificial intelligence begins improving itself? The Recursive Loop explores how recursive self-improvement could work, what is already possible and what remains beyond our reach. Combining technical depth with critical analysis, it examines the opportunities, risks and profound implications for the future of AI and human civilization.
A hands-on guide to recovering governing equations from data with symbolic regression, SINDy, and PDE discovery. Every method is built from scratch in Python, with the discipline to tell a genuine law from a plausible fit.
A short, tool-agnostic field guide to what AI really changes at the unit, integration and end-to-end levels of testing, and how to adopt it without losing trust in your suite.
Discover how diffusion models work and learn to build them from the ground up. From the mathematics behind image generation to hands-on PyTorch implementations, this book guides you through training, fine-tuning and deploying powerful generative AI systems. Gain the knowledge and practical skills to engineer diffusion models of your own, from first principles to production.
A hands-on, method-first guide that takes you from “what is data?” to professional practice: cleaning, analysing, visualizing, and reporting data, then working with AI to do it faster. Clear thinking and honest numbers are the skills that outlast every tool.
Stop treating neural networks and loss.backward() as a black box. Build a complete automatic differentiation engine and deep learning library from an empty folder in 100% pure Python—from ScalarNode computation graphs and reverse-mode backpropagation to Multi-Layer Perceptrons, AdamW, BatchNorm1D, and a Character-Level Language Model—explained with visual split-box diagrams, plain-English intuition, and verifiable terminal outputs.
Stop treating Stable Diffusion as a black box. Build a complete, verifiable Text-to-Image Latent Diffusion engine from an empty folder in pure PyTorch—from the Variational Autoencoder (VAE) and CLIP Text Encoder to the Time-Conditioned U-Net, DDPM Noise Scheduler, and Classifier-Free Guidance—explained with crystal-clear visual diagrams, plain-English intuition, and zero hidden magic.
RAG answers you can trace to a source: ingestion, permissions, hybrid search, reranking, evals and regression gates, drawn and built in Python.
Large language models can write code, solve problems and reason about the world, but how do they actually work? The Ghost in the Weights takes you inside the black box, exploring the tools and techniques researchers use to uncover the algorithms hidden in neural networks. Learn to trace circuits, decode features and turn opaque computations into something you can understand, test and investigate yourself.
Discover how artificial intelligence is transforming scientific research, from hypothesis generation to autonomous experimentation. This book explores the models, algorithms and computational tools driving a new era of discovery, offering researchers and engineers the knowledge to understand, build and apply AI-powered scientific systems.
Go beyond a plausible patch: trace its impact, choose meaningful tests, and make the merge decision reviewable.
Turn useful results into lessons your AI workflow can test, retain and apply again.