Books

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

800 pages. 11 chapters. The full forecasting stack in Python — from ARIMA to foundation models — with production-grade code and proper evaluation. No hype.

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

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.

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.

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.

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.

이 책은 면접 준비, 프로젝트 진행, 또는 순수한 지적 호기심을 위해 대규모 언어 모델의 내부 구조와 작동 원리를 이해하고 싶은 모든 분들을 위한, 그림으로 설명하는 핵심 가이드입니다.

Este libro es una guía concisa e ilustrada para cualquiera que desee comprender el funcionamiento interno de los Grandes Modelos de Lenguaje, ya sea de cara a realizar entrevistas, proyectos o para satisfacer su curiosidad.

Artificial Intelligence is not merely about data, learning, or neural networks—it is fundamentally about exploring vast spaces of possibilities.Every search algorithm, planning system, optimization framework, recommendation engine, and machine learning model faces a common challenge: navigating an enormous combinatorial universe of potential solutions.In Combinatorial Thinking in Artificial Intelligence, Anshuman Mishra reveals the mathematical foundations that drive modern AI systems. Through permutations, combinations, graph theory, probability, search strategies, and optimization techniques, readers learn how intelligent systems reason, search, and make decisions in complex environments.If you want to understand why AI algorithms work—not just how to implement them—this book provides the missing mathematical perspective.Discover the combinatorial engine behind intelligence.

A Sample Learning Journey with This Book Imagine a final-year MCA student who needs to select a project topic.·        After Chapter-3, they can identify a novel, research-worthy problem.·        By Chapter-5, they will know how to collect, clean, and preprocess relevant data.·        Using Chapter-6 and 8, they can implement a fair and unbiased ML model.·        Through Chapter-9 and 10, they can interpret results with statistical confidence.·        By Chapter-11, they will have the skills to write a publication-ready paper.In short, the book transforms a student project into publishable research.

4. Who Should Read This Book?This book is specially designed for a wide audience:4.1 StudentsStudents of:Artificial intelligenceData scienceComputer scienceInformation technologyOperations researchApplied mathematicswill find this book essential for understanding foundations and applications of intelligent decision-making.4.2 ResearchersThis book helps researchers explore:Decision-making modelsPlanning algorithmsRisk-aware AIMathematical modelingOptimization under uncertaintyIt helps form a strong base for research projects and PhD work.4.3 Industry ProfessionalsEngineers and developers working on:RoboticsAutonomous vehiclesDecision support systemsPredictive analyticsAI toolsFinancial modelingwill find the algorithms, pseudocode, and frameworks highly practical.4.4 Faculty MembersTeachers and professors can use this book as:A primary textbookA reference guideA source of problems and case studiesA foundation for graduate and research courses 5. Learning OutcomesAfter studying this book, readers will be able to:Understand and construct utility functionsEvaluate rational choices under uncertaintyBuild decision treesConstruct influence diagramsDesign sequential decision systemsFormulate and solve MDPsApply POMDPs to real problemsImplement classical planning algorithmsModel multi-agent interactions using game theoryApply Bayesian decision theory to uncertain environmentsUnderstand the foundation of reinforcement learningBuild real-world decision and planning systemsThis ensures comprehensive mastery of both theory and practice.

این کتاب راهنمایی مختصر و تصویری است برای افرادی که می‌خواهند سازوکارهای مدل‌های زبانی بزرگ را در مصاحبه‌ها، پروژه‌ها یا حتی برای رفع کنجکاوی شخصی‌شان بهتر درک کنند.

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.

Building production-grade AI systems requires more than just calling an API or running a basic notebook—it demands mastery over hardware constraints, memory bandwidth limits, and distributed inference architectures.​My new book, AI Systems Engineering: From Prototype to Production, is now officially available. It’s a code-first, rigorous engineering manual covering everything from vLLM runtime internals, PagedAttention, and FP8/INT4 quantization to HNSW vector search, hybrid RAG, and autonomous multi-agent swarm architectures.​Stop wrestling with out-of-memory errors and sub-optimal latency. Master the infrastructure that powers modern AI at scale.