Artificial Intelligence

Zefs Guide to Deep Learning is a short guide to the most important concepts in deep learning, the technique at the center of the current artificial intelligence revolution. It will give you a strong understanding of the core ideas and most important methods and applications. All in around only 150 pages!

You don't need another "intro to LLMs" tutorial. You need patterns—proven architectural blueprints that tell you exactly when to use RAG vs. fine-tuning, how to build agents that don't spiral, and why your retrieval pipeline returns garbage. This book gives you 29 of them, with architecture diagrams and working Python code. Free. No fluff. No vendor lock-in.

Understanding the most common mistakes in machine learning will allow you not only to avoid them, but to build better machine learning systems and less prone to errors. After reading this book, you will be ready to build more robust and trustworthy machine learning models.

Your AI prototype works. Now ship it. Most AI frameworks are built for exploration. kdeps is built for production. Define your agent in YAML, declare its dependencies, and deploy it anywhere — Docker, Kubernetes, a standalone binary, an edge device — without rewriting a line when you switch LLM providers. AI Appliances is the hands-on guide to building autonomous AI agents and multi-agent systems with kdeps: deterministic pipelines, real error handling, real deployment, and no vendor lock-in. Write YAML. Run anywhere. Own everything.

Move beyond chatbots. Learn how to build autonomous AI agents that execute real business workflows 24/7 and scale operations at a fraction of traditional costs.

Digitale Transformation war das Hype-Thema vor KI. Es gibt allerdings einen nicht geringen Anteil an Fach- und Führungskräften, deren Wissen darüber weiter ausbaufähig ist. Dieses Buch ist eine Einführung für alle diejenigen, die keine "digitalen Pioniere" sind, sondern wissen wollen, was aus dem Thema Digitalisierung auf sie zukommen kann und aus dem Thema KI zusätzlich auf sie zukommen wird.

A strategic, executive-level guide to making the most of your company's AI efforts.

Every deep learning tutorial shows you the code. Almost none show you the idea. This is the book to read first - before the frameworks, before the maths notation, before the course you've already paid for. One example, followed all the way through, from a random guess to a network that works. By the end you'll understand what backpropagation actually does, why gradients matter, and what's really happening while your model trains. No calculus required.

Software changed its front door: we don't open apps anymore; we talk to an assistant. Learn to build for that world —a real AI-native app with MCP, OAuth, and LLMs— using AI as your copilot. From zero to production.

El software cambió de puerta de entrada: ya no abrimos apps, le hablamos a un asistente. Aprende a construir para ese mundo —una app AI-native real con MCP, OAuth y LLMs— usando la IA como copiloto. De cero a producción.

This book gives senior technology leaders a practical operating system for enterprise AI strategy. It turns scattered pilots into a board-ready plan by walking through strategy, economics, vendor decisions, ownership, governance, GenAI architecture, and roadmap assembly: AI Platform Scorecard, Use-Case Prioritization Matrix, Budget Model + Cost Guardrails, Vendor Decision Framework, RACI Matrix.

Close the gap between "AI that generates code" and "AI-assisted development for production software" with this complete, proven playbook including the six-phase arc from audit to production.

A book about the one thing no amount of AI changes: the fact that you have exactly one brain The archive of human knowledge doubles faster than any mind can follow it. Mendel’s genetics waited thirty-four years to be read. A quarter-million new theorems are proved each year that no single mathematician can survey. Elan Moritz calls the boundary where individual cognition runs out the one brain barrier 

Write your comments first, and let Copilot generate the code.