AI Foundations and Applications by Manning

Practical techniques to accelerate software development using generative AI. Let’s get real. You’d like to hand off a lot of tedious software development tasks to an assistant—and now you can! AI-powered coding tools like Copilot can accelerate research, design, code creation, testing, troubleshooting, documentation, refactoring and more. Coding with AI shows you how. Written for working developers, this book fast-tracks you to AI-powered productivity with bite-size projects, tested prompts, and techniques for getting the most out of AI. In Coding with AI you’ll learn how to: • Incorporate AI tools into your development workflow • Create pro-quality documentation and tests • Debug and refactor software efficiently • Create and organize reusable prompts Coding with AI takes you through several small Python projects with the help of AI tools, showing you exactly how to use AI to create and refine real software. This book skips the baby steps and goes straight to the techniques you’ll use on the job, every day. You’ll learn to sidestep AI inefficiencies like hallucination and identify the places where AI can save you the most time and effort. Unique tips, tricks, and prompt hacks ensure you’re getting the best out of AI. About the book Coding with AI is a deep dive into AI coding tools, quickly getting you up to speed with effective code generation in a professional development environment. You’ll benefit from author Jeremy Morgan’s clear-eyed developer-to-developer approach based on his real-world experience of AI coding. Hands-on Python projects demonstrate how you can use AI to organize prompts, create documentation, debug your software, and more. About the reader For professional software developers. Examples in Python. About the author Jeremy Morgan is on a mission to help developers get better at what they do. He's a Senior Training Architect for KodeKloud and an avid tech blogger and speaker. He has two decades of experience as an engineer building software for everything from Fortune 100 companies to tiny startups. Jeremy hosts the popular tech blog, www.jeremymorgan.com. He also contributes to open source as a .NET Foundation Member, DevOps Institute Ambassador, and serves on a DevNetwork advisory board. Get a free eBook (PDF or ePub) from Manning as well as access to the online liveBook format (and its AI assistant that will answer your questions in any language) when you purchase the print book.

Generative AI can transform your business by streamlining the process of creating text, images, and code. This book will show you how to get in on the action! Generative AI in Action is the comprehensive and concrete guide to generative AI you’ve been searching for. It introduces both AI’s fundamental principles and its practical applications in an enterprise context—from generating text and images for product catalogs and marketing campaigns, to technical reporting, and even writing software. Inside, author Amit Bahree shares his experience leading Generative AI projects at Microsoft for nearly a decade, starting well before the current GPT revolution. Inside Generative AI in Action you will find: • A practical overview of of generative AI applications • Architectural patterns, integration guidance, and best practices for generative AI • The latest techniques like RAG, prompt engineering, and multi-modality • The challenges and risks of generative AI like hallucinations and jailbreaks • How to integrate generative AI into your business and IT strategy Generative AI in Action is full of real-world use cases for generative AI, showing you where and how to start integrating this powerful technology into your products and workflows. You’ll benefit from tried-and-tested implementation advice, as well as application architectures to deploy GenAI in production at enterprise scale. About the technology In controlled environments, deep learning systems routinely surpass humans in reading comprehension, image recognition, and language understanding. Large Language Models (LLMs) can deliver similar results in text and image generation and predictive reasoning. Outside the lab, though, generative AI can both impress and fail spectacularly. So how do you get the results you want? Keep reading! About the book Generative AI in Action presents concrete examples, insights, and techniques for using LLMs and other modern AI technologies successfully and safely. In it, you’ll find practical approaches for incorporating AI into marketing, software development, business report generation, data storytelling, and other typically-human tasks. You’ll explore the emerging patterns for GenAI apps, master best practices for prompt engineering, and learn how to address hallucination, high operating costs, the rapid pace of change and other common problems. What's inside • Best practices for deploying Generative AI apps • Production-quality RAG • Adapting GenAI models to your specific domain About the reader For enterprise architects, developers, and data scientists interested in upgrading their architectures with generative AI. About the author Amit Bahree is Principal Group Product Manager for the Azure AI engineering team at Microsoft. The technical editor on this book was Wee Hyong Tok. Table of Contents Part 1 1 Introduction to generative AI 2 Introduction to large language models 3 Working through an API: Generating text 4 From pixels to pictures: Generating images 5 What else can AI generate? Part 2 6 Guide to prompt engineering 7 Retrieval-augmented generation: The secret weapon 8 Chatting with your data 9 Tailoring models with model adaptation and fine-tuning Part 3 10 Application architecture for generative AI apps 11 Scaling up: Best practices for production deployment 12 Evaluations and benchmarks 13 Guide to ethical GenAI: Principles, practices, and pitfalls A The book’s GitHub repository B Responsible AI tools

AI-Powered Search teaches you the latest machine-learning techniques. Ideal for software developers or data scientists familiar with the basics of search engine development, it will show you ways to create content that will constantly get smarter and automatically deliver better, more relevant search experiences.

Get the eBook free when you register your print book at Manning. This book introduces deep learning from scratch with examples that use the R language and the Keras library. Each chapter offers practical code examples that build your understanding of deep learning layer by layer. You’ll appreciate the intuitive explanations, crisp illustrations, and clear examples. In this expanded third edition you’ll find fresh chapters on the transformers architecture, building your own GPT-like large language model, and image generation with diffusion models. Plus, even DL veterans will benefit from the insightful explanations on the nature of deep learning. For R programmers, the R interface to the Keras deep learning library is a powerful head start on building deep learning models without switching to Python. It provides a simple, consistent API that makes deep learning accessible and simplifies the process of building neural networks, even if you have no prior experience in advanced machine learning. In Deep Learning with R, Third Edition you will learn: • Deep learning from first principles • The latest features of Keras • Image classification and image segmentation • Time series forecasting • Text classification and machine translation • Text and image generation—build your own LLMs and diffusion models! • Scaling and tuning models About the technology Deep Learning with R, Third Edition is a practical, concept-driven introduction to modern deep learning for R users. With a focus on clarity, intuition, and hands-on experimentation, it guides you from the foundations of deep learning to advanced architectures such as transformers and LLMs. This book treats R as a fully capable environment for modern deep learning, showing how contemporary models and workflows can be developed end to end without compromise. About the book Deep Learning with R, Third Edition gets you up to speed with the current state of deep learning practice. Using Keras 3 with R, you’ll build and train neural networks from scratch, work with transformers, fine-tune pretrained models and explore large language models and diffusion-based image generation. By following carefully constructed examples that build insight step-by-step, you’ll develop a deep understanding of why these models work—not just how to use them. What's inside • Hands-on, code-first learning in R • A clear progression from deep learning fundamentals to generative AI • Examples that emphasize intuition and understanding About the reader For readers with intermediate R skills. No prior experience with deep learning is required. About the author François Chollet is the creator of Keras and author of Deep Learning with Python. Tomasz Kalinowski is a software engineer at Posit Software, PBC and maintainer of the Keras and TensorFlow R packages. Table of Contents 1 What is deep learning? 2 The mathematical building blocks of neural networks 3 Introduction to TensorFlow, PyTorch, JAX, and Keras 4 Classification and regression 5 Fundamentals of machine learning 6 The universal workflow of machine learning 7 A deep dive into Keras 8 Image classification 9 Convnet architecture patterns 10 Interpreting what convnets learn 11 Image segmentation 12 Object detection 13 Timeseries forecasting 14 Text classification 15 Language models and the Transformer 16 Text generation 17 Image generation 18 Best practices for the real world 19 The future of AI 20 Conclusions

Probabilistic Deep Learning is a hands-on guide to the principles that support neural networks. Learn to improve network performance with the right distribution for different data types, and discover Bayesian variants that can state their own uncertainty to increase accuracy. This book provides easy-to-apply code and uses popular frameworks to keep you focused on practical applications. Summary Probabilistic Deep Learning: With Python, Keras and TensorFlow Probability teaches the increasingly popular probabilistic approach to deep learning that allows you to refine your results more quickly and accurately without much trial-and-error testing. Emphasizing practical techniques that use the Python-based Tensorflow Probability Framework, you’ll learn to build highly-performant deep learning applications that can reliably handle the noise and uncertainty of real-world data. Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications. About the technology The world is a noisy and uncertain place. Probabilistic deep learning models capture that noise and uncertainty, pulling it into real-world scenarios. Crucial for self-driving cars and scientific testing, these techniques help deep learning engineers assess the accuracy of their results, spot errors, and improve their understanding of how algorithms work. About the book Probabilistic Deep Learning is a hands-on guide to the principles that support neural networks. Learn to improve network performance with the right distribution for different data types, and discover Bayesian variants that can state their own uncertainty to increase accuracy. This book provides easy-to-apply code and uses popular frameworks to keep you focused on practical applications. What's inside Explore maximum likelihood and the statistical basis of deep learning Discover probabilistic models that can indicate possible outcomes Learn to use normalizing flows for modeling and generating complex distributions Use Bayesian neural networks to access the uncertainty in the model About the reader For experienced machine learning developers. About the author Oliver Dürr is a professor at the University of Applied Sciences in Konstanz, Germany. Beate Sick holds a chair for applied statistics at ZHAW and works as a researcher and lecturer at the University of Zurich. Elvis Murina is a data scientist. Table of Contents PART 1 - BASICS OF DEEP LEARNING 1 Introduction to probabilistic deep learning 2 Neural network architectures 3 Principles of curve fitting PART 2 - MAXIMUM LIKELIHOOD APPROACHES FOR PROBABILISTIC DL MODELS 4 Building loss functions with the likelihood approach 5 Probabilistic deep learning models with TensorFlow Probability 6 Probabilistic deep learning models in the wild PART 3 - BAYESIAN APPROACHES FOR PROBABILISTIC DL MODELS 7 Bayesian learning 8 Bayesian neural networks

How to implement LLM attention mechanisms and GPT-style transformers. In Build a Large Language Model (from Scratch) bestselling author Sebastian Raschka guides you step by step through creating your own LLM. Each stage is explained with clear text, diagrams, and examples. You’ll go from the initial design and creation, to pretraining on a general corpus, and on to fine-tuning for specific tasks. Build a Large Language Model (from Scratch) teaches you how to: • Plan and code all the parts of an LLM • Prepare a dataset suitable for LLM training • Fine-tune LLMs for text classification and with your own data • Use human feedback to ensure your LLM follows instructions • Load pretrained weights into an LLM Build a Large Language Model (from Scratch) takes you inside the AI black box to tinker with the internal systems that power generative AI. As you work through each key stage of LLM creation, you’ll develop an in-depth understanding of how LLMs work, their limitations, and their customization methods. Your LLM can be developed on an ordinary laptop, and used as your own personal assistant. About the technology Physicist Richard P. Feynman reportedly said, “I don’t understand anything I can’t build.” Based on this same powerful principle, bestselling author Sebastian Raschka guides you step by step as you build a GPT-style LLM that you can run on your laptop. This is an engaging book that covers each stage of the process, from planning and coding to training and fine-tuning. About the book Build a Large Language Model (From Scratch) is a practical and eminently-satisfying hands-on journey into the foundations of generative AI. Without relying on any existing LLM libraries, you’ll code a base model, evolve it into a text classifier, and ultimately create a chatbot that can follow your conversational instructions. And you’ll really understand it because you built it yourself! What's inside • Plan and code an LLM comparable to GPT-2 • Load pretrained weights • Construct a complete training pipeline • Fine-tune your LLM for text classification • Develop LLMs that follow human instructions About the reader Readers need intermediate Python skills and some knowledge of machine learning. The LLM you create will run on any modern laptop and can optionally utilize GPUs. About the author Sebastian Raschka, PhD, is an LLM Research Engineer with over a decade of experience in artificial intelligence. His work spans industry and academia, including implementing LLM solutions as a senior engineer at Lightning AI and teaching as a statistics professor at the University of Wisconsin–Madison. Sebastian collaborates with Fortune 500 companies on AI solutions and serves on the Open Source Board at University of Wisconsin–Madison. He specializes in LLMs and the development of high-performance AI systems, with a deep focus on practical, code-driven implementations. He is the author of the bestselling books Machine Learning with PyTorch and Scikit-Learn, and Machine Learning Q and AI. The technical editor on this book was David Caswell. Table of Contents 1 Understanding large language models 2 Working with text data 3 Coding attention mechanisms 4 Implementing a GPT model from scratch to generate text 5 Pretraining on unlabeled data 6 Fine-tuning for classification 7 Fine-tuning to follow instructions A Introduction to PyTorch B References and further reading C Exercise solutions D Adding bells and whistles to the training loop E Parameter-efficient fine-tuning with LoRA

Create and improve conversational AI with the latest patterns, best practices, and tools, including generative AI models. Conversational AI (CAI) tools are built to solve problems, but all-too-often they just end up causing pain for users–and developers! Effective Conversational AI reveals best practices and industry-tested techniques for creating chatbots and conversational AI tools that are reliable at an enterprise scale. With the tested ideas and examples in this book, you’ll learn to build chatbots that your customers and colleagues will actually want to use! In Effective Conversational AI you’ll learn how to: • Create high-quality chatbots and other conversational AI experiences • Plan for continuous improvement • Incorporate generative AI solutions to improve quality, accuracy, and usability • Evaluate user experience and business results Effective Conversational AI introduces continuous improvement practices that are vital for the constant betterment and evolution of chatbots and CAI tools. It introduces the three most-common forms of chatbot—Q&A, process-oriented, and routing agents—and presents a reliable framework for continuously improving each one. Using modern generative AI and tried-and-tested classic approaches, you’ll learn to deliver high performance chatbots that can guide a customer through complex end-to-end tasks—no human required! Foreword by Jesús Mantas. About the technology Powerful new chatbot frameworks and Generative AI models can practically eliminate problems like misinterpreting user intent and delivering nonsensical answers. In this book, you’ll learn how to build chatbots that take advantage of large language models and other modern tools and create conversational AI experiences users will love. About the book Effective Conversational AI teaches you how to build great chatbots that perform reliably even at enterprise scale. In it, you’ll learn how to clarify user intent using LLMs, respond accurately to unanticipated input, and use Retrieval Augmented Generation to keep responses up to date. Along the way, you’ll discover how to establish a feedback loop for continuous quality improvement and master techniques to integrate GenAI safely into conventional chatbot designs. What's inside • Blend Generative AI and conventional chatbot tools • Use LLMs to improve quality, accuracy, and usability • Plan for continuous improvement • Domain-specific responses using RAG About the reader For developers, engineers, and product managers working with conversational AI. About the author Andrew Freed, Cari Jacobs, and Eniko Rózsa are seasoned conversational AI developers with IBM. Table of Contents Part 1 1 What makes conversational AI work? 2 Building a conversational AI 3 Planning for improvement Part 2 4 Understanding what your users really want 5 Improving weak understanding for traditional AI 6 Enhancing responses with retrieval-augmented generation 7 Augmenting intent data with generative AI Part 3 8 Streamlining complex flows 9 Harnessing context for an adaptive virtual assistant experience 10 Reducing complexity with generative AI Part 4 11 Reducing opt-outs 12 Conversational summarization for smooth handoff

In AI Agents in Action, you'll learn how to build production-ready assistants, multi-agent systems, and behavioral agents. You'll master the essential parts of an agent, including retrieval-augmented knowledge and memory, while you create multi-agent applications that can use software tools, plan tasks autonomously, and learn from experience. As you explore the many interesting examples, you'll work with state-of-the-art tools like OpenAI Assistants API, GPT Nexus, LangChain, Prompt Flow, AutoGen, and CrewAI.

The bestselling book on Python deep learning, now covering generative AI, Keras 3, PyTorch, and JAX! Deep Learning with Python, Third Edition puts the power of deep learning in your hands. This new edition includes the latest Keras and TensorFlow features, generative AI models, and added coverage of PyTorch and JAX. Learn directly from the creator of Keras and step confidently into the world of deep learning with Python. In Deep Learning with Python, Third Edition you’ll discover: • Deep learning from first principles • The latest features of Keras 3 • A primer on JAX, PyTorch, and TensorFlow • Image classification and image segmentation • Time series forecasting • Large Language models • Text classification and machine translation • Text and image generation—build your own GPT and diffusion models! • Scaling and tuning models With over 100,000 copies sold, Deep Learning with Python makes it possible for developers, data scientists, and machine learning enthusiasts to put deep learning into action. In this expanded and updated third edition, Keras creator François Chollet offers insights for both novice and experienced machine learning practitioners. You'll master state-of-the-art deep learning tools and techniques, from the latest features of Keras 3 to building AI models that can generate text and images. About the technology In less than a decade, deep learning has changed the world—twice. First, Python-based libraries like Keras, TensorFlow, and PyTorch elevated neural networks from lab experiments to high-performance production systems deployed at scale. And now, through Large Language Models and other generative AI tools, deep learning is again transforming business and society. In this new edition, Keras creator François Chollet invites you into this amazing subject in the fluid, mentoring style of a true insider. About the book Deep Learning with Python, Third Edition makes the concepts behind deep learning and generative AI understandable and approachable. This complete rewrite of the bestselling original includes fresh chapters on transformers, building your own GPT-like LLM, and generating images with diffusion models. Each chapter introduces practical projects and code examples that build your understanding of deep learning, layer by layer. What's inside • Hands-on, code-first learning • Comprehensive, from basics to generative AI • Intuitive and easy math explanations • Examples in Keras, PyTorch, JAX, and TensorFlow About the reader For readers with intermediate Python skills. No previous experience with machine learning or linear algebra required. About the author François Chollet is the co-founder of Ndea and the creator of Keras. Matthew Watson is a software engineer at Google working on Gemini and a core maintainer of Keras. Table of Contents 1 What is deep learning? 2 The mathematical building blocks of neural networks 3 Introduction to TensorFlow, PyTorch, JAX, and Keras 4 Classification and regression 5 Fundamentals of machine learning 6 The universal workflow of machine learning 7 A deep dive on Keras 8 Image classification 9 ConvNet architecture patterns 10 Interpreting what ConvNets learn 11 Image segmentation 12 Object detection 13 Timeseries forecasting 14 Text classification 15 Language models and the Transformer 16 Text generation 17 Image generation 18 Best practices for the real world 19 The future of AI 20 Conclusions

Separate the AI facts from the AI fiction, and discover how you can best put these tools to work in your organization. In Inside AI AI professor and entrepreneur Dr. Akli Adjaoute puts AI in perspective, with informed insights from 30 years spent in the field. His book lays out a pragmatic blueprint that every leader can utilize to drive innovation with artificial intelligence. In Inside AI you’ll learn how to: Gain insight into diverse AI techniques and methodologies Learn from both successful and failed AI applications Identify the capabilities and limitations of AI systems Understand successful and failed uses of AI in business See where human cognition still exceeds AI Bust common myths like AI’s threat to jobs and civilization Manage AI projects effectively Inside AI takes you on a journey through artificial intelligence, from AI’s origins in traditional expert systems all the way to deep learning and Large Language Models. There’s no hype here—you’ll get the grounded, evidence-based insights that are vital for making strategic decisions and preparing your business for the future. About the technology Artificial Intelligence enthusiasts promise everything from human-like collaboration on everyday tasks to the end of work as we know it. Is AI just a flash in the pan, or can it really transform how you do business? This intriguing book sifts through the hype and separates the truth from the myths, with clear advice on what AI can—and can’t—achieve. About the book Inside AI provides a clear-headed overview of modern artificial intelligence, including the recent advances of Generative AI and Large Language Models. Its accessible and jargon-free explanations of leading AI techniques showcase how AI delivers tangible advantages to businesses. Both inspiring and practical, this book provides a proven framework for developing successful AI applications. What's inside Insights from successful and failed AI applications A survey of AI techniques and methodologies Bust common AI myths Manage AI projects effectively About the reader For anyone seeking grounded insights into AI’s capabilities, including business leaders and decision makers. About the author Akli Adjaoute is the founder of multiple AI-related companies. He served as an adjunct professor at the University of San Francisco and as Scientific Committee Chair and Head of the AI department at EPITA. The technical editor on this book was Richard Vaughan. Table of contents 1 The rise of machine intelligence 2 AI mastery: Essential techniques, Part 1 3 AI mastery: Essential techniques, Part 2 4 Smart agent technology 5 Generative AI and large language models 6 Human vs. machine 7 AI doesn’t turn data into intelligence 8 AI doesn’t threaten our jobs 9 Technological singularity is absurd 10 Learning from successful and failed applications of AI 11 Next-generation AI A Tracing the roots: From mechanical calculators to digital dreams B Algorithms and programming languages

Learn how generative AI works by building your very own models that can write coherent text, create realistic images, and even make lifelike music. Learn Generative AI with PyTorch teaches the underlying mechanics of generative AI by building working AI models from scratch. Throughout, you’ll use the intuitive PyTorch framework that’s instantly familiar to anyone who’s worked with Python data tools. Along the way, you’ll master the fundamentals of General Adversarial Networks (GANs), Transformers, Large Language Models (LLMs), variational autoencoders, diffusion models, LangChain, and more! In Learn Generative AI with PyTorch you’ll build these amazing models: • A simple English-to-French translator • A text-generating model as powerful as GPT-2 • A diffusion model that produces realistic flower images • Music generators using GANs and Transformers • An image style transfer model • A zero-shot know-it-all agent The generative AI projects you create use the same underlying techniques and technologies as full-scale models like GPT-4 and Stable Diffusion. You don’t need to be a machine learning expert—you can get started with just some basic Python programming skills. About the technology Transformers, Generative Adversarial Networks (GANs), diffusion models, LLMs, and other powerful deep learning patterns have radically changed the way we manipulate text, images, and sound. Generative AI may seem like magic at first, but with a little Python, the PyTorch framework, and some practice, you can build interesting and useful models that will train and run on your laptop. This book shows you how. About the book Learn Generative AI with PyTorch introduces the underlying mechanics of generative AI by helping you build your own working AI models. You’ll begin by creating simple images using a GAN, and then progress to writing a language translation transformer line-by-line. As you work through the fun and fascinating projects, you’ll train models to create anime images, write like Hemingway, make music like Mozart, and more. You just need Python and a few machine learning basics to get started. You’ll learn the rest as you go! What's inside • Build an English-to-French translator • Create a text-generation LLM • Train a diffusion model to produce high-resolution images • Music generators using GANs and Transformers About the reader Examples use simple Python. No deep learning experience required. About the author Mark Liu is the founding director of the Master of Science in Finance program at the University of Kentucky. The technical editor on this book was Emmanuel Maggiori.

Automate and accelerate your everyday IT tasks with instant solutions! What if you never had to write another after-incident report, piece of boilerplate code, or a performance review from scratch ever again? Use AI tools like ChatGPT, Claude, Gemini, and Copilot right, and you’ll take back hours of your time—and more! AI for Everyday IT reveals how you can automate dozens of your daily IT tasks with generative AI. In AI for Everyday IT you’ll learn how to: • Write effective prompts for common IT tasks • Optimize report generation, document handling, and workplace communication • Resolve IT conflicts and crises • Acquire new skills and upgrade your resume • AI for help desk, database administration and systems administration • Incorporate AI into DevOps processes and create AI-powered applications • Simplify time-consuming people management tasks In this hands-on guide, automation experts Chrissy LeMaire and Brandon Abshire show you how AI tools like ChatGPT have made their lives a million times easier, and how they can do the same for you. You’ll find proven strategies for using AI to improve help desk support, automate sysadmin and database tasks, aid with DevOps engineering, handle managing IT teams, and dozens more time-saving and quality-improving hacks. Foreword by Nitya Narasimhan. About the technology Have you lost days sifting through logs to find a latency issue? AI can do it in seconds! Need to update your documentation? Mere moments for AI. Are you writing scripts, designing data recovery strategies, and evaluating network designs? AI can handle it all—if you know how to use it. About the book AI for Everyday IT shows you exactly how AI can transform support desk operations, root cause analysis, disaster recovery planning—even writing professional emails when you’re too furious to be nice! This instantly-useful guide has time-saving techniques for all IT pros—from devs and DBAs to technical writers and product managers. Each relatable example is fully illustrated with the prompts and problem formulation strategies, along with interesting insights and anecdotes from authors Chrissy Lemaire and Brandon Abshire. What's inside • Document handling and workplace communication • Database administration and development • DevOps engineering and AI powered apps • People management and career planning About the reader Whether you’re working in operations, development, management, or security, you’ll love these productivity hacks for generative AI. No previous AI experience required. About the author Chrissy LeMaire is a dual Microsoft MVP and GitHub Star, the creator of dbatools, and author of the Manning book Learn dbatools in a Month of Lunches. Brandon Abshire has spent over twenty years in IT, including roles at a leading Fortune 500 semiconductor and telecommunications company and multiple top-ranked US hospital systems.

PyTorch core developer Howard Huang updates the bestselling original Deep Learning with PyTorch with new insights into the transformers architecture and generative AI models. Instantly familiar to anyone who knows PyData tools like NumPy, PyTorch simplifies deep learning without sacrificing advanced features. In this book you’ll learn how to create your own neural network and deep learning systems and take full advantage of PyTorch’s built-in tools for automatic differentiation, hardware acceleration, distributed training, and more. You’ll discover how easy PyTorch makes it to build your entire DL pipeline, including using the PyTorch Tensor API, loading data in Python, monitoring training, and visualizing results. Each new technique you learn is put into action with practical code examples in each chapter, culminating into you building your own convolution neural networks, transformers, and even a real-world medical image classifier. In Deep Learning with PyTorch, Second Edition you’ll find: • Deep learning fundamentals reinforced with hands-on projects • Mastering PyTorch's flexible APIs for neural network development • Implementing CNNs, transformers, and diffusion models • Optimizing models for training and deployment • Generative AI models to create images and text About the technology The powerful PyTorch library makes deep learning simple—without sacrificing the features you need to create efficient neural networks, LLMs, and other ML models. Pythonic by design, it’s instantly familiar to users of NumPy, Scikit-learn, and other ML frameworks. This thoroughly-revised second edition covers the latest PyTorch innovations, including how to create and refine generative AI models. About the book Deep Learning with PyTorch, Second Edition shows you how to build neural network models using the latest version of PyTorch. Clear explanations and practical projects help you master the fundamentals and explore advanced architectures including transformers and LLMs. Along the way you’ll learn techniques for training using augmented data, improving model architecture, and fine tuning. What's inside • PyTorch APIs for neural network development • LLMs, transformers, and diffusion models • Model training and deployment About the reader For Python programmers with a background in machine learning. About the author Howard Huang is a software engineer and developer on the PyTorch library focusing on large scale, distributed training. Eli Stevens, Luca Antiga, and Thomas Viehmann authored the first edition of Deep Learning with PyTorch. Table of Contents Part 1 1 Introducing deep learning and the PyTorch library 2 Pretrained networks 3 It starts with a tensor 4 Real-world data representation using tensors 5 The mechanics of learning 6 Using a neural network to fit the data 7 Telling birds from airplanes: Learning from images 8 Using convolutions to generalize Part 2 9 How transformers work 10 Diffusion models for images 11 Using PyTorch to fight cancer 12 Combining data sources into a unified dataset 13 Training a classification model to detect suspected tumors 14 Improving training with metrics and augmentation 15 Using segmentation to find suspected nodules 16 Training models on multiple GPU

Get a free eBook (PDF or ePub) from Manning as well as access to the online liveBook format (and its AI assistant that will answer your questions in any language) when you purchase the print book. AI tools like ChatGPT and Gemini, automated coding tools like Cursor and Copilot, and countless LLM-powered agents have become a part of daily life. They’ve also spawned a storm of misinformation, hype, and doomsaying that makes it tough to understand exactly what Generative AI actually is and what it can really do. This book delivers a clear, well-written survey of generative AI fundamentals along with the techniques and strategies you need to use AI safely and effectively. It guides you from your first eye-opening interaction with tools like ChatGPT to how AI tools can transform your personal and professional life safely and responsibly. AI moves fast—and so this second edition has been completely revised to reflect the latest developments in the field. In this easy-to-read introduction, you’ll learn: • How large language models (LLMs) work • How to apply AI across personal and professional work • The social, legal, and policy landscape around generative AI • Emerging trends like reasoning models and vibe coding About the technology Generative AI tools like ChatGPT, Gemini, and Claude can draft emails, generate marketing copy, and prototype product designs. They can also produce poetry, realistic images or videos, and even generate computer code. But how do they do all that? This accessible book reveals how generative AI works in plain, jargon-free language, so you can use it safely and effectively. About the book Introduction to Generative AI, Second Edition is a completely revised and updated guide to the capabilities, risks, and limitations of generative AI. You’ll understand the latest innovations in AI, AI agents, multimodal training, reasoning models, retrieval-augmented generation (RAG), and more. Along the way, you’ll explore how AI is impacting the world, with an expert-level look at AI in industry, education, and society. What's inside • How AI and foundation models work • Applications across daily life and work • Balancing innovation with responsibility About the reader No technical experience required. About the author Numa Dhamani is a natural language processing expert working at the intersection of technology and society. Maggie Engler is a researcher and engineer working on safety for generative AI systems. Table of Contents 1 Large language models: The foundation of generative AI 2 Training large language models: Learning at scale 3 Data privacy and safety: Technical and legal controls 4 AI and the creative economy: Innovation and intellectual property 5 Misuse and adversarial attacks: Challenges and responsible testing 6 Machine-augmented work: Productivity, education, and economy 7 Prompt engineering: Strategies for guiding and evaluating LLMs 8 AI agents: The rise of autonomous AI systems 9 Human connections: The social role of chatbots 10 The future of responsible AI: Risks, practices, and policy 11 Frontiers of AI: Open questions and global trends

The mathematical paradigms that underlie deep learning typically start out as hard-to-read academic papers, often leaving engineers in the dark about how their models actually function. Math and Architectures of Deep Learning bridges the gap between theory and practice, laying out the math of deep learning side by side with practical implementations in Python and PyTorch. Written by deep learning expert Krishnendu Chaudhury, you'll peer inside the "black box" to understand how your code is working, and learn to comprehend cutting-edge research you can turn into practical applications. about the technology It's important to understand how your deep learning models work, both so that you can maintain them efficiently and explain them to other stakeholders. Learning mathematical foundations and neural network architecture can be challenging, but the payoff is big. You'll be free from blind reliance on pre-packaged DL models and able to build, customize, and re-architect for your specific needs. And when things go wrong, you'll be glad you can quickly identify and fix problems. about the book Math and Architectures of Deep Learning sets out the foundations of DL in a way that's both useful and accessible to working practitioners. Each chapter explores a new fundamental DL concept or architectural pattern, explaining the underpinning mathematics and demonstrating how they work in practice with well-annotated Python code. You'll start with a primer of basic algebra, calculus, and statistics, working your way up to state-of-the-art DL paradigms taken from the latest research. By the time you're done, you'll have a combined theoretical insight and practical skills to identify and implement DL architecture for almost any real-world challenge.

Discover best practices, reproducible architectures, and design patterns to help guide deep learning models from the lab into production. In Deep Learning Patterns and Practices you will learn: Internal functioning of modern convolutional neural networks Procedural reuse design pattern for CNN architectures Models for mobile and IoT devices Assembling large-scale model deployments Optimizing hyperparameter tuning Migrating a model to a production environment The big challenge of deep learning lies in taking cutting-edge technologies from R&D labs through to production. Deep Learning Patterns and Practices is here to help. This unique guide lays out the latest deep learning insights from author Andrew Ferlitsch’s work with Google Cloud AI. In it, you'll find deep learning models presented in a unique new way: as extendable design patterns you can easily plug-and-play into your software projects. Each valuable technique is presented in a way that's easy to understand and filled with accessible diagrams and code samples. Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications. About the technology Discover best practices, design patterns, and reproducible architectures that will guide your deep learning projects from the lab into production. This awesome book collects and illuminates the most relevant insights from a decade of real world deep learning experience. You’ll build your skills and confidence with each interesting example. About the book Deep Learning Patterns and Practices is a deep dive into building successful deep learning applications. You’ll save hours of trial-and-error by applying proven patterns and practices to your own projects. Tested code samples, real-world examples, and a brilliant narrative style make even complex concepts simple and engaging. Along the way, you’ll get tips for deploying, testing, and maintaining your projects. What's inside Modern convolutional neural networks Design pattern for CNN architectures Models for mobile and IoT devices Large-scale model deployments Examples for computer vision About the reader For machine learning engineers familiar with Python and deep learning. About the author Andrew Ferlitsch is an expert on computer vision, deep learning, and operationalizing ML in production at Google Cloud AI Developer Relations. Table of Contents PART 1 DEEP LEARNING FUNDAMENTALS 1 Designing modern machine learning 2 Deep neural networks 3 Convolutional and residual neural networks 4 Training fundamentals PART 2 BASIC DESIGN PATTERN 5 Procedural design pattern 6 Wide convolutional neural networks 7 Alternative connectivity patterns 8 Mobile convolutional neural networks 9 Autoencoders PART 3 WORKING WITH PIPELINES 10 Hyperparameter tuning 11 Transfer learning 12 Data distributions 13 Data pipeline 14 Training and deployment pipeline

Summary Grokking Deep Learning teaches you to build deep learning neural networks from scratch! In his engaging style, seasoned deep learning expert Andrew Trask shows you the science under the hood, so you grok for yourself every detail of training neural networks. Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications. About the Technology Deep learning, a branch of artificial intelligence, teaches computers to learn by using neural networks, technology inspired by the human brain. Online text translation, self-driving cars, personalized product recommendations, and virtual voice assistants are just a few of the exciting modern advancements possible thanks to deep learning. About the Book Grokking Deep Learning teaches you to build deep learning neural networks from scratch! In his engaging style, seasoned deep learning expert Andrew Trask shows you the science under the hood, so you grok for yourself every detail of training neural networks. Using only Python and its math-supporting library, NumPy, you'll train your own neural networks to see and understand images, translate text into different languages, and even write like Shakespeare! When you're done, you'll be fully prepared to move on to mastering deep learning frameworks. What's inside The science behind deep learning Building and training your own neural networks Privacy concepts, including federated learning Tips for continuing your pursuit of deep learning About the Reader For readers with high school-level math and intermediate programming skills. About the Author Andrew Trask is a PhD student at Oxford University and a research scientist at DeepMind. Previously, Andrew was a researcher and analytics product manager at Digital Reasoning, where he trained the world's largest artificial neural network and helped guide the analytics roadmap for the Synthesys cognitive computing platform. Table of Contents Introducing deep learning: why you should learn it Fundamental concepts: how do machines learn? Introduction to neural prediction: forward propagation Introduction to neural learning: gradient descent Learning multiple weights at a time: generalizing gradient descent Building your first deep neural network: introduction to backpropagation How to picture neural networks: in your head and on paper Learning signal and ignoring noise:introduction to regularization and batching Modeling probabilities and nonlinearities: activation functions Neural learning about edges and corners: intro to convolutional neural networks Neural networks that understand language: king - man + woman == ? Neural networks that write like Shakespeare: recurrent layers for variable-length data Introducing automatic optimization: let's build a deep learning framework Learning to write like Shakespeare: long short-term memory Deep learning on unseen data: introducing federated learning Where to go from here: a brief guide

This book shows you step-by-step and example-by-example how to build sites and applications that take advantage of large language models (LLMs) like GPT, Claude, and Llama. Written especially for web developers comfortable with React or Next.js, this book introduces the tools and techniques you need to add sophisticated AI features like Retrieval Augmented Generation (RAG), document summarization, chatbots, and more to your web-based projects. It guides you through AI development using only JavaScript and other common web dev skills–no Python or Machine Learning experience required. You’ll learn by working with full-scale AI projects that solve actual business problems. You’ll soon be delivering user-friendly, efficient interfaces that make the absolute best use of AI tech. In Build AI-Enhanced Web Apps you'll learn how to: • Integrate AI models into React and Next.js applications • Implement streaming responses and real-time AI interactions • Manage conversation history and context in chat applications • Implement LangChain.js for complex AI workflows and reasoning • Build a web application for summarizing documents using LangChain.js • Utilize Retrieval-Augmented Generation (RAG) systems for knowledge management • Develop an AI-powered interview preparation system with voice feedback About the technology The users have spoken! Agents, personalized responses, and other LLM-powered features are required in modern web applications. Build AI-Enhanced Web Apps presents the end-to-end architecture of AI web apps, including UI, backend infrastructure, data processing, API integration, deployment, and scaling, with examples and language perfect for professional web developers. About the book This accessible book shows you how to ship real AI features—not just toy demos—using a JavaScript stack you already know: React for UI, Next.js for backend integration, and the Vercel AI SDK to connect to LLMs like Gemini and GPT. In it, you’ll acquire the skills you need to complete two portfolio-ready projects: a voice-based interview assistant and a RAG-powered corporate knowledge system. You’ll also learn how to design workflows that balance latency, cost, and UX and implement responsible guardrails for security, quality control, hallucinations, and bias. What's inside • Build AI features using a professional stack • Ship production-ready features • Learn from concrete projects About the reader For web developers familiar with JavaScript and React. About the author Theo Despoudis is a Senior Engineer at WP Engine specializing in AI-powered search and headless WordPress. He is an expert in integrating LLMs, RAG, and Vercel AI SDK into React and Next.js apps. Table of Contents Part 1 1 Using generative AI in web apps 2 Building your first generative AI web application 3 Connecting AI models with the Vercel AI SDK 4 Managing conversation and state in your application Part 2 5 Prompt engineering in web applications 6 Building AI workflows with LangChain.js 7 Document summarization and RAG with LangChain.js 8 Testing and debugging techniques 9 Deployment and security Part 3 10 Building an AI interview assistant: Project walk-through 11 Building an AI RAG agent: Project walk-through Part 4 12 Integrating web apps with the Model Context Protocol A Running the examples

Deep Learning with Structured Data teaches you powerful data analysis techniques for tabular data and relational databases. Summary Deep learning offers the potential to identify complex patterns and relationships hidden in data of all sorts. Deep Learning with Structured Data shows you how to apply powerful deep learning analysis techniques to the kind of structured, tabular data you'll find in the relational databases that real-world businesses depend on. Filled with practical, relevant applications, this book teaches you how deep learning can augment your existing machine learning and business intelligence systems. Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications. About the technology Here’s a dirty secret: Half of the time in most data science projects is spent cleaning and preparing data. But there’s a better way: Deep learning techniques optimized for tabular data and relational databases deliver insights and analysis without requiring intense feature engineering. Learn the skills to unlock deep learning performance with much less data filtering, validating, and scrubbing. About the book Deep Learning with Structured Data teaches you powerful data analysis techniques for tabular data and relational databases. Get started using a dataset based on the Toronto transit system. As you work through the book, you’ll learn how easy it is to set up tabular data for deep learning, while solving crucial production concerns like deployment and performance monitoring. What's inside When and where to use deep learning The architecture of a Keras deep learning model Training, deploying, and maintaining models Measuring performance About the reader For readers with intermediate Python and machine learning skills. About the author Mark Ryan is a Data Science Manager at Intact Insurance. He holds a Master's degree in Computer Science from the University of Toronto. Table of Contents 1 Why deep learning with structured data? 2 Introduction to the example problem and Pandas dataframes 3 Preparing the data, part 1: Exploring and cleansing the data 4 Preparing the data, part 2: Transforming the data 5 Preparing and building the model 6 Training the model and running experiments 7 More experiments with the trained model 8 Deploying the model 9 Recommended next steps

AI-powered applications are rapidly becoming the new normal. Personal productivity assistants, coding agents, smarter search, and automated reporting tools are popping up everywhere. The LangChain ecosystem, and standards like MCP are driving this new gold rush. This book helps you claim your spot. This is your hands-on guide to creating real, production-ready language model solutions. With LangChain and LangGraph, you’ll orchestrate powerful agentic workflows and build dynamic tool-based agents that can search, summarize, reason, and act. You’ll move from essential prompt engineering to advanced Retrieval Augmented Generation (RAG), and finally to deploying multi-agent systems using modern integration standards like the Model Context Protocol (MCP). In AI Agents and Applications: With LangChain, LangGraph and MCP, you’ll discover: • Prompt and context engineering for accurate, hallucination-resistant systems • Advanced RAG for summarization, semantic search, and reliable Q&A • Structured, multi-step agentic workflows with LangGraph • Tool-based agents that adapt in real time • Multi-agent systems for complex, real-world tasks • MCP integration to expose, compose, and consume plug-and-play tools About the technology This book teaches you to design reliable LLM-powered systems by focusing on the concepts, architectures, and design patterns that will stay stable even as models and APIs change. You’ll learn to structure prompts, compose modular chains, and build RAG pipelines that ingest documents, split them into chunks, embed them, retrieve the right context, and ground answers to elliminate (or vastly reduce) hallucinations. About the book Along the way you’ll build concrete applications—summarization and Q&A engines, context-aware chatbots with memory, and tool-using AI agents that orchestrate multi-step workflows with branching logic. For the examples, the book uses Python, LangChain, LangGraph, and LangSmith, but you’ll be able to generalize to other frameworks. You’ll understand with clarity and confidence how to keep integrations maintainable, manage context limits and cost/latency tradeoffs, and evaluate, debug, and monitor behavior so your systems work in production. About the author Roberto Infante is an AI innovator with deep FinTech experience, working for a London-based hedge fund. He specializes in building agentic systems for both plain vanilla and exotic quantitative analysis. Table of Contents Part 1 1 Introduction to AI agents and applications 2 Executing prompts programmatically Part 2 3 Summarizing text using LangChain 4 Building a research summarization engine 5 Agentic workflows with LangGraph Part 3 6 RAG fundamentals with ChromaDB 7 Q&A chatbots with LangChain and LangSmith Part 4 8 Advanced indexing 9 Question transformations 10 Query generation, routing, and retrieval postprocessing Part 5 11 Building tool-based agents with LangGraph 12 Multi-agent systems

"The JAX numerical computing library tackles the core performance challenges at the heart of deep learning and other scientific computing tasks. By combining Google's Accelerated Linear Algebra platform (XLA) with a hyper-optimized version of NumPy and a variety of other high-performance features, JAX delivers a huge performance boost in low-level computations and transformations. Deep learning with JAX is a hands-on guide to using JAX for deep learning and other mathematically-intensive applications. Google Developer Expert Grigory Sapunov steadily builds your understanding of JAX's concepts. The engaging examples introduce the fundamental concepts on which JAX relies and then show you how to apply them to real-world tasks. You'll learn how to use JAX's ecosystem of high-level libraries and modules, and also how to combine TensorFlow and PyTorch with JAX for data loading and deployment" --Publisher's description.

Learn how large language models like GPT and Gemini work under the hood in plain English. How Large Language Models Work translates years of expert research on Large Language Models into a readable, focused introduction to working with these amazing systems. It explains clearly how LLMs function, introduces the optimization techniques to fine-tune them, and shows how to create pipelines and processes to ensure your AI applications are efficient and error-free. In How Large Language Models Work you will learn how to: • Test and evaluate LLMs • Use human feedback, supervised fine-tuning, and Retrieval Augmented Generation (RAG) • Reducing the risk of bad outputs, high-stakes errors, and automation bias • Human-computer interaction systems • Combine LLMs with traditional ML How Large Language Models Work is authored by top machine learning researchers at Booz Allen Hamilton, including researcher Stella Biderman, Director of AI/ML Research Drew Farris, and Director of Emerging AI Edward Raff. They lay out how LLM and GPT technology works in plain language that’s accessible and engaging for all. About the Technology Large Language Models put the “I” in “AI.” By connecting words, concepts, and patterns from billions of documents, LLMs are able to generate the human-like responses we’ve come to expect from tools like ChatGPT, Claude, and Deep-Seek. In this informative and entertaining book, the world’s best machine learning researchers from Booz Allen Hamilton explore foundational concepts of LLMs, their opportunities and limitations, and the best practices for incorporating AI into your organizations and applications. About the Book How Large Language Models Work takes you inside an LLM, showing step-by-step how a natural language prompt becomes a clear, readable text completion. Written in plain language, you’ll learn how LLMs are created, why they make errors, and how you can design reliable AI solutions. Along the way, you’ll learn how LLMs “think,” how to design LLM-powered applications like agents and Q&A systems, and how to navigate the ethical, legal, and security issues. What’s Inside • Customize LLMs for specific applications • Reduce the risk of bad outputs and bias • Dispel myths about LLMs • Go beyond language processing About the Readers No knowledge of ML or AI systems is required. About the Author Edward Raff, Drew Farris and Stella Biderman are the Director of Emerging AI, Director of AI/ML Research, and machine learning researcher at Booz Allen Hamilton. Table of Contents 1 Big picture: What are LLMs? 2 Tokenizers: How large language models see the world 3 Transformers: How inputs become outputs 4 How LLMs learn 5 How do we constrain the behavior of LLMs? 6 Beyond natural language processing 7 Misconceptions, limits, and eminent abilities of LLMs 8 Designing solutions with large language models 9 Ethics of building and using LLMs Get a free eBook (PDF or ePub) from Manning as well as access to the online liveBook format (and its AI assistant that will answer your questions in any language) when you purchase the print book.

See how an AI assistant can bring your ideas to life immediately! Once, to be a programmer you had to write every line of code yourself. Now tools like GitHub Copilot can instantly generate working programs based on your description in plain English. An instant bestseller, Learn AI-Assisted Python Programming has taught thousands of aspiring programmers how to write Python the easy way—with the help of AI. It’s perfect for beginners, or anyone who’s struggled with the steep learning curve of traditional programming. In Learn AI-Assisted Python Programming, Second Edition you’ll learn how to: • Write fun and useful Python applications—no programming experience required! • Use the GitHub Copilot AI coding assistant to create Python programs • Write prompts that tell Copilot exactly what to do • Read Python code and understand what it does • Test your programs to make sure they work the way you want them to • Fix code with prompt engineering or human tweaks • Apply Python creatively to help out on the job AI moves fast, and so the new edition of Learn AI-Assisted Python Programming, Second Edition is fully updated to take advantage of the latest models and AI coding tools. Written by two esteemed computer science university professors, it teaches you everything you need to start programming Python in an AI-first world. You’ll learn skills you can use to create working apps for data analysis, automating tedious tasks, and even video games. Plus, in this new edition, you’ll find groundbreaking techniques for breaking down big software projects into smaller tasks AI can easily achieve. Foreword by Beth Simon. About the technology The way people write computer programs has changed forever. Using GitHub Copilot, you describe in plain English what you want your program to do, and the AI generates it instantly. About the book This book shows you how to create and improve Python programs using AI—even if you’ve never written a line of computer code before. Spend less time on the slow, low-level programming details and instead learn how an AI assistant can bring your ideas to life immediately. As you go, you’ll even learn enough of the Python language to understand and improve what your AI assistant creates. What's inside • Prompts for working code • Tweak code manually and with AI help • AI-test your programs • Let AI handle tedious details About the reader If you can move files around on your computer and install new programs, you can learn to write useful software! About the author Dr. Leo Porter is a Teaching Professor at UC San Diego. Dr. Daniel Zingaro is an Associate Teaching Professor at the University of Toronto. The technical editor on this book was Peter Morgan. Table of Contents 1 Introducing AI-assisted programming with GitHub Copilot 2 Getting started with Copilot 3 Designing functions 4 Reading Python code: Part 1 5 Reading Python code: Part 2 6 Testing and prompt engineering 7 Problem decomposition 8 Debugging and better understanding your code 9 Automating tedious tasks 10 Making some games 11 Creating an authorship identification program 12 Future directions

Build AI models that can reliably deliver causal inference. How do you know what might have happened, had you done things differently? Causal AI gives you the insight you need to make predictions and control outcomes based on causal relationships instead of pure correlation, so you can make precise and timely interventions. Causal AI is a practical introduction to building AI models that can reason about causality. In Causal AI you will learn how to: • Build causal reinforcement learning algorithms • Implement causal inference with modern probabilistic machine tools such as PyTorch and Pyro • Compare and contrast statistical and econometric methods for causal inference • Set up algorithms for attribution, credit assignment, and explanation • Convert domain expertise into explainable causal models Author Robert Osazuwa Ness, a leading researcher in causal AI at Microsoft Research, brings his unique expertise to this cutting-edge guide. His clear, code-first approach explains essential details of causal machine learning that are hidden in academic papers. Everything you learn can be easily and effectively applied to industry challenges, from building explainable causal models to predicting counterfactual outcomes. Foreword by Lindsay Edwards. About the technology Traditional ML models can’t answer causal questions like, “Why did that happen?” or, “What factors should I change to get a particular outcome?” This book blends advanced statistical methods, computational techniques, and new algorithms to create machine learning systems that automate the process of causal inference. About the book Causal AI introduces the tools, techniques, and algorithms of causal reasoning for machine learning. This unique book masterfully blends Bayesian and probabilistic approaches to causal inference with practical hands-on examples in Python. Along the way, you’ll learn to integrate causal assumptions into deep learning architectures, including reinforcement learning and large language models. You’ll also use PyTorch, Pyro, and other ML libraries to scale up causal inference. What's inside • End-to-end causal inference with DoWhy • Deep Bayesian causal generative AI models • A code-first tour of the do-calculus and Pearl’s causal hierarchy • Code for fine-tuning causal large language models About the reader For data scientists and machine learning engineers. Examples in Python. About the author Robert Osazuwa Ness is an AI researcher at Microsoft Research and professor at Northeastern University. He is a contributor to open-source causal inference packages such as Python’s DoWhy and R’s bnlearn. Table of Contents Part 1 1 Why causal AI 2 A primer on probabilistic generative modeling Part 2 3 Building a causal graphical model 4 Testing the DAG with causal constraints 5 Connecting causality and deep learning Part 3 6 Structural causal models 7 Interventions and causal effects 8 Counterfactuals and parallel worlds 9 The general counterfactual inference algorithm 10 Identification and the causal hierarchy Part 4 11 Building a causal inference workflow 12 Causal decisions and reinforcement learning 13 Causality and large language models

Evolutionary Deep Learning is a guide to improving your deep learning models with AutoML enhancements based on the principles of biological evolution. This exciting new approach utilizes lesser-known AI approaches to boost performance without hours of data annotation or model hyperparameter tuning. In this one-of-a-kind guide, you'll discover tools for optimizing everything from data collection to your network architecture.

Great data presentations tell a story. Learn how to organize, visualize, and present data using Python, generative AI, and the cutting-edge Altair data visualization toolkit. Take the fast track to amazing data presentations! Data Storytelling with Altair and AI introduces a stack of useful tools and tried-and-tested methodologies that will rapidly increase your productivity, streamline the visualization process, and leave your audience inspired. In Data Storytelling with Altair and AI you’ll discover: • Using Python Altair for data visualization • Using Generative AI tools for data storytelling • The main concepts of data storytelling • Building data stories with the DIKW pyramid approach • Transforming raw data into a data story Data Storytelling with Altair and AI teaches you how to turn raw data into effective, insightful data stories. You’ll learn exactly what goes into an effective data story, then combine your Python data skills with the Altair library and AI tools to rapidly create amazing visualizations. Your bosses and decision-makers will love your new presentations—and you’ll love how quick Generative AI makes the whole process! About the technology Every dataset tells a story. After you’ve cleaned, crunched, and organized the raw data, it’s your job to share its story in a way that connects with your audience. Python’s Altair data visualization library, combined with generative AI tools like Copilot and ChatGPT, provide an amazing toolbox for transforming numbers, code, text, and graphics into intuitive data presentations. About the book Data Storytelling with Altair and AI teaches you how to build enhanced data visualizations using these tools. The book uses hands-on examples to build powerful narratives that can inform, inspire, and motivate. It covers the Altair data visualization library, along with AI techniques like generating text with ChatGPT, creating images with DALL-E, and Python coding with Copilot. You’ll learn by practicing with each interesting data story, from tourist arrivals in Portugal to population growth in the USA to fake news, salmon aquaculture, and more. What's inside • The Data-Information-Knowledge-Wisdom (DIKW) pyramid • Publish data stories using Streamlit, Tableau, and Comet • Vega and Vega-Lite visualization grammar About the reader For data analysts and data scientists experienced with Python. No previous knowledge of Altair or Generative AI required. About the author Angelica Lo Duca is a researcher at the Institute of Informatics and Telematics of the National Research Council, Italy. The technical editor on this book was Ninoslav Cerkez. Table of Contents PART 1 1 Introducing data storytelling 2 Running your first data story in Altair and GitHub Copilot 3 Reviewing the basic concepts of Altair 4 Generative AI tools for data storytelling PART 2 5 Crafting a data story using the DIKW pyramid 6 From data to information: Extracting insights 7 From information to knowledge: Building textual context 8 From information to knowledge: Building the visual context 9 From knowledge to wisdom: Adding next steps PART 3 10 Common issues while using generative AI 11 Publishing the data story A Technical requirements B Python pandas DataFrameC Other chart types

Artificial intelligence algorithms are the backbone of search and optimization, deep learning, reinforcement learning, and, of course, generative AI. This book introduces the most important AI algorithms using relatable illustrations, interesting examples, and thought-provoking exercises. Written in simple language and with lots of visual references and hands-on code examples, it helps you build a natural intuition into how intelligent systems learn, plan, and adapt. This second edition has been thoroughly revised, with new chapters on large language models, image generation, and more. You know you can solve a problem with AI—but how? Which algorithm do you pick and how do you properly implement it? This book makes it simple and easy to understand the most core and common AI approaches. You’ll learn how to understand problem types, map real-world tasks to those problems, and how to design and implement the right algorithm—all following clear visual examples, pseudocode, and learning-oriented examples. In Grokking AI Algorithms, Second Edition you will discover: • How to pick the right algorithm for each AI problem • Learn the fundamentals of search (the foundation of modern AI) • Building intelligent agents to solve puzzles • Finding solutions using the theory of evolution and genetic algorithms • Make predictions with neural networks • Understand how AI gets better with reinforcement learning • Building a LLM pipeline and image diffusion model from scratch About the technology AI algorithms are the backbone of search and optimization problems, deep learning, reinforcement learning, and, of course, generative AI. But knowing which algorithm to use—and why—is often harder than writing the code itself. Grokking AI Algorithms, Second Edition illuminates the algorithms behind modern generative AI with clear explanations, step-by-step code examples, and beautifully simple illustrations. About the book Everything you’ll learn in this powerfully simple book is reinforced through engaging, end-to-end projects—from solving mazes with search algorithms to navigating a car through a crowded parking lot with reinforcement learning. Plus, this second edition has been thoroughly revised with fresh chapters exploring the core algorithms of LLMs and image generation models. What's inside • Search algorithms and swarm optimization • Deep learning and neural networks • Training AI with reinforcement learning • Building a LLM pipeline for text generation About the reader Requires beginning to intermediate programming skills and high school level mathematics. No AI experience required. About the author Rishal Hurbans is an experienced technologist and serial entrepreneur specializing in AI engineering and human performance. Table of Contents 1 Intuition of AI 2 Search fundamentals 3 Intelligent search 4 Evolutionary algorithms 5 Advanced evolutionary approaches 6 Swarm intelligence: Ants 7 Swarm intelligence: Particles 8 Machine learning 9 Artificial neural networks 10 Reinforcement learning 11 Large language models 12 Generative image models