Books

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

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.

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.

A chatbot can describe how to do your work. An agent can do it—if you build it to be trusted. Learn to construct, verify, and deploy AI agents that earn a place in real scientific and engineering practice.

Every intelligent system faces a fundamental challenge:How do you find the best solution when there are millions—or even trillions—of possibilities?From A* search and heuristic optimization to neural architecture search, hyperparameter tuning, constraint satisfaction, and quantum optimization, modern AI depends on sophisticated strategies for navigating combinatorial search spaces.In this advanced second volume, Anshuman Mishra explores the powerful algorithms that enable intelligent systems to search smarter, optimize faster, and scale beyond brute force computation.Discover how combinatorial thinking drives machine learning, optimization, quantum AI, and the future of intelligent decision-making.The future of AI belongs to those who understand combinatorial complexity.

5. How This Book is Useful for StudyThis book is carefully designed to meet the needs of students, teachers, and researchers in computer science, artificial intelligence, and applied mathematics. Here’s how it will benefit learners:1.     Conceptual Clarity: The book explains abstract concepts like fuzzy sets, fuzzy logic, and fuzzy inference in simple and student-friendly language.2.     Step-by-Step Approach: Mathematical derivations, examples, and solved problems are provided in a logical sequence.3.     Exam-Oriented Content: The text covers topics that are important for BCA, MCA, B.Tech, M.Tech, and UGC NET examinations.4.     Practical Relevance: Numerous case studies and applications in AI systems are provided, making the subject practical and engaging.5.     Interdisciplinary Approach: The book connects mathematics, computer science, and engineering, preparing students for multidisciplinary research.6.     Hands-On Learning: Exercises, numerical problems, and small projects are suggested for practice.7.     Self-Study Friendly: Designed in such a way that even students without a strong background in higher mathematics can grasp the concepts.In summary, this book transforms fuzzy mathematics from a theoretical subject into a practical skill set essential for AI study and research. 6. Why This Book is Different and ImportantWhile there are many books on fuzzy logic or AI separately, very few combine mathematical foundations with AI applications in such a comprehensive, student-oriented way.·        Balanced Coverage: Unlike purely theoretical texts, this book strikes a balance between mathematical rigor and practical applications.·        Accessible Style: Concepts are explained in simple terms, supported with examples, diagrams, and illustrations.·        Focus on Students: Written with examination and career needs in mind, making it directly useful for academic success.·        AI-Oriented Approach: Unlike classical fuzzy mathematics books, this one emphasizes how fuzzy tools integrate into AI systems.·        Future-Ready Content: Emerging areas like fuzzy deep learning, quantum fuzzy logic, and hybrid systems are included to prepare students for future research.This makes the book not just a textbook, but a career-building guide for students of AI. 7. Pedagogical FeaturesTo make learning engaging and effective, the book is structured with special features such as:·        Definitions and Key Points highlighted for quick revision.·        Illustrations and Diagrams for visual understanding.·        Solved Examples to demonstrate problem-solving techniques.·        Exercises and Practice Problems at the end of each chapter.·        Case Studies to connect theory with real-life AI applications.·        Summary Sections for quick review before exams. 8. Who Should Read This Book? (Target Audience)This book is intended for a wide range of learners:·        Undergraduate Students (BCA, B.Sc., B.Tech): To build a foundation in fuzzy mathematics and AI.·        Postgraduate Students (MCA, M.Sc., M.Tech): For advanced study and research in AI and soft computing.·        Competitive Exam Aspirants (UGC NET, GATE): As a reference guide for key topics in AI and fuzzy logic.·        Researchers and Scholars: To explore applications of fuzzy systems in machine learning, NLP, and robotics.·        Industry Professionals: To understand the practical applications of fuzzy logic in AI-based projects. 9. Practical Outcomes After Studying the BookBy the end of this book, readers will be able to:·        Understand the mathematical foundations of fuzzy sets, relations, and logic.·        Apply fuzzy reasoning to solve uncertain and imprecise problems.·        Design fuzzy inference systems and controllers for AI applications.·        Implement fuzzy clustering and decision-making models in machine learning.·        Integrate fuzzy systems with neural networks and genetic algorithms.·        Contribute to research in advanced areas like fuzzy deep learning and quantum fuzzy logic.This ensures that learners not only gain theoretical knowledge but also practical competence in applying fuzzy mathematics in AI.

WHO SHOULD READ THIS BOOK?This book is ideal for:·        BCA, MCA, B.Tech, M.Tech students·        UGC NET aspirants·        AI/ML researchers·        Data scientists·        AI developers·        University professors·        PhD scholars·        Industry professionals working with black-box models·        Anyone who wants mathematical clarity on XAIIts writing style balances mathematical rigor with readability, making it useful for self-study and classroom use. TEACHING & LEARNING BENEFITS·        50+ diagrams, proofs, and mathematical derivations.·        Step-by-step logical flow for each model.·        Case studies from healthcare, finance, law, and engineering.·        Practical coding references (without over-reliance on tools).·        Integration of statistics, calculus, causality, and deep learning.·        Real-world examples for intuitive understanding.·        Problems at the end of each chapter (optional addition).Instructors can adopt this book for academic courses in:·        Explainable AI·        Machine Learning·        Statistical Inference·        Causality·        Artificial Intelligence Foundations·        Deep Learning Interpretability UNIQUE CONTRIBUTIONS OF THIS BOOKUnlike other XAI or ML books, this work by Anshuman Mishra offers:·        Mathematical derivations for SHAP, IG, LIME, and other explainability tools.·        Original proofs for fairness properties in attribution methods.·        Detailed causal diagrams and do-calculus explanations.·        A structured approach to XAI evaluation metrics.·        Coverage of transformer explainability—rare in academic books.·        Clarity in blending classical mathematical theory with modern AI systems.This makes the book a reference-level resource for the next decade of AI learning.

Geopolitics is too late. Discover how the Naciro Engine uses AI to measure the pulse of nations in real-time, providing a 15-minute recalibration of global truth and power. Check the live data on https://nationfiles.com

Master deep learning with PyTorch & Lightning. Core concepts, practical Q&A, and production-ready code with a full companion GitHub repository.

Our starting point was raw CIFAR-10 bytes and a compiler check, and we ended up with residual networks, coroutine pipelines, compressed checkpoints and a real-time classifier built on two cooperating threads.Whenever we introduced a new technique, we gave it a contract, tested it early and measured it honestly. Our concepts rejected the wrong types before a build was finished, and static assertions caught shape mistakes long before training. Every claim in these chapters had an output we could reproduce.

A research monograph connecting quantum annealing, Aizenberg MVN theory and complex spectral surrogate models, with detailed applications to battery energy storage placement in power grids.

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.

What really happens inside a neural network? This book explores the tools and ideas researchers use to uncover how AI systems work, from foundational concepts to practical experiments. Learn to separate solid findings from bold claims, develop useful research skills and prepare for a field that is changing as quickly as the technology itself.