Artificial Intelligence

The first book that addresses engineering management specifically for the AI-native era. Classic EM books like The Manager's Path and An Elegant Puzzle predate agentic coding tools — this one starts where they left off. Every chapter produces a concrete artifact: a hiring rubric, a performance calibration guide, a budget template, a rollout plan. By the end, you have a complete management playbook for leading engineering teams where agents write most of the code.

Bridge AI and science with this hands-on guide. Whether you're a researcher learning ML or an engineer entering scientific applications, build real systems across chemistry, biology, physics & climate. Master Transformers, Diffusion Models & GNNs for scientific discovery. 500+ pages, 50+ Colab notebooks. Design molecules, predict proteins, accelerate climate models—all hands-on, zero setup required.

AI coding agents can move fast, but speed without clear intent creates expensive mistakes. This practical guide shows how Behavior-Driven Development turns specifications into a reliable contract between you and autonomous coding systems, helping agents build the right thing, catch problems earlier and produce software you can trust.

Modern Deep Learning models can be extremely large, often exceeding the memory capacity of a single GPU or CPU. In these cases, training must be distributed across multiple processors. This introduces the need for high-speed communication between GPUs—both within a single server and across multiple servers. Intra-node GPU communication typically relies on high-speed interconnects like NVLink, with Direct Memory Access operations enabling efficient data transfers between GPUs. Inter-node communication, however, depends on the backend network, either  InfiniBand or Ethernet-based. Synchronization of model parameters across GPUs places strict requirements on the network: high throughput, ultra-low latency, and zero packet loss. Achieving this in an Ethernet fabric is challenging but possible.   This is where datacenter networking meets Deep Learning. Understanding how GPUs communicate and what the network must deliver is essential for designing effective AI data center infrastructures.

AI is changing the way we find and fix software vulnerabilities. Intelligent Discovery explores the techniques behind this shift, from static analysis to AI-driven vulnerability research and automated repair. With a clear-eyed look at both the potential and the pitfalls, it shows what these tools can do, where they fall short and why human expertise still matters.

Build production-grade RAG systems in C# — from an 80-line Hello World to a fully deployed Azure pipeline with the Microsoft Agent Framework, MCP, GraphRAG, multi-agent orchestration, eval gates, and EU AI Act-ready audit trails. 682 pages, 25 chapters, one evolving enterprise project, every line of code runnable in .NET 10.

Büyük dil modellerine dair ana kavramları ve pratik uygulamaları kapsayan, açık ve görsellerle desteklenmiş bir rehber. Projeler, mülakatlar ve kişisel öğrenme için idealdir.

You don’t need massive compute or big-tech resources to build real AI. This hands-on guide shows you how to build and fine-tune your own small language model—from scratch—using accessible tools like Google Colab. Learn transformers step-by-step, train and align models on your own data, and deploy practical AI systems that run on consumer GPUs. If you’ve ever wondered “Can I build my own model?”—this book proves the answer is yes.

Your AI builder made an app that works. This book shows you whether it's also leaking your API keys, your users' data or your source code, and gives you copy-paste prompts so the same AI can fix it before a stranger finds it.

A Comprehensive Engineering Guide to Low-Precision AI, Quantized Inference, GPU Kernels, and Production DeploymentQuantization is one of the key techniques for making large language models more efficient. By representing weights, activations, and other model data at reduced precision, engineers can lower memory requirements, improve hardware utilization, and potentially increase inference throughput. Achieving these benefits, however, requires careful trade-offs between numerical accuracy, computational cost, memory bandwidth, and hardware support. Mastering LLM Quantization: Architecture and Code is a 44-chapter engineering reference covering the mathematics, algorithms, implementation techniques, GPU kernels, evaluation methods, and deployment systems behind quantized language models. It connects theoretical foundations with practical approaches to building and optimizing low-precision inference pipelines.

Discover the power of thinking in logic. This hands-on guide takes you from your first Prolog query to advanced techniques in constraints, grammars, AI search, meta-programming and production development. With clear explanations and executable SWI-Prolog examples, you’ll learn not just how Prolog works, but how to use it well.

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

By the time you finish this book, you should be able to make your systems observable across microservices, AI workloads, security monitoring, and hybrid cloud infrastructure. This book will help you learn how to effectively instrument, generate, collect, and export telemetry data (metrics, logs, and traces) to analyze your software’s performance and behavior.

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。

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.