{"product_id":"machine-learning-upgrade-isbn-9781394249633","title":"Machine Learning Upgrade","description":"\u003cp\u003e\u003cb\u003eA much-needed guide to implementing new technology in workspaces \u003c\/b\u003e \u003c\/p\u003e\u003cp\u003eFrom experts in the field comes \u003ci\u003eMachine Learning Upgrade: A Data Scientist's Guide to MLOps, LLMs, and ML Infrastructure,\u003c\/i\u003e a book that provides data scientists and managers with best practices at the intersection of management, large language models (LLMs), machine learning, and data science. This groundbreaking book will change the way that you view the pipeline of data science. The authors provide an introduction to modern machine learning, showing you how it can be viewed as a holistic, end-to-end system—not just shiny new gadget in an otherwise unchanged operational structure. By adopting a data-centric view of the world, you can begin to see unstructured data and LLMs as the foundation upon which you can build countless applications and business solutions. This book explores a whole world of decision making that hasn't been codified yet, enabling you to forge the future using emerging best practices. \u003c\/p\u003e\u003cul\u003e \u003cli\u003eGain an understanding of the intersection between large language models and unstructured data\u003c\/li\u003e \u003cli\u003eFollow the process of building an LLM-powered application while leveraging MLOps techniques such as data versioning and experiment tracking\u003c\/li\u003e \u003cli\u003eDiscover best practices for training, fine tuning, and evaluating LLMs\u003c\/li\u003e \u003cli\u003eIntegrate LLM applications within larger systems, monitor their performance, and retrain them on new data\u003c\/li\u003e \u003c\/ul\u003e \u003cp\u003eThis book is indispensable for data professionals and business leaders looking to understand LLMs and the entire data science pipeline. \u003c\/p\u003e\u003cp\u003eIntroduction ix\u003c\/p\u003e \u003cp\u003e\u003cb\u003e1 A Gentle Introduction to Modern Machine Learning 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eData Science Is Diverging from Business Intelligence 3\u003c\/p\u003e \u003cp\u003eFrom CRISP-DM to Modern, Multicomponent ml Systems 4\u003c\/p\u003e \u003cp\u003eThe Emergence of LLMs Has Increased ML’s Power and Complexity 7\u003c\/p\u003e \u003cp\u003eWhat You Can Expect from This Book 9\u003c\/p\u003e \u003cp\u003e\u003cb\u003e2 An End-to-End Approach 11\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eComponents of a YouTube Search Agent 13\u003c\/p\u003e \u003cp\u003ePrinciples of a Production Machine Learning System 16\u003c\/p\u003e \u003cp\u003eObservability 19\u003c\/p\u003e \u003cp\u003eReproducibility 19\u003c\/p\u003e \u003cp\u003eInteroperability 20\u003c\/p\u003e \u003cp\u003eScalability 21\u003c\/p\u003e \u003cp\u003eImprovability 22\u003c\/p\u003e \u003cp\u003eA Note on Tools 23\u003c\/p\u003e \u003cp\u003e\u003cb\u003e3 A Data-Centric View 25\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eThe Emergence of Foundation Models 25\u003c\/p\u003e \u003cp\u003eThe Role of Off-the-Shelf Components 27\u003c\/p\u003e \u003cp\u003eThe Data-Driven Approach 28\u003c\/p\u003e \u003cp\u003eA Note on Data Ethics 28\u003c\/p\u003e \u003cp\u003eBuilding the Dataset 30\u003c\/p\u003e \u003cp\u003eWorking with Vector Databases 34\u003c\/p\u003e \u003cp\u003eData Versioning and Management 50\u003c\/p\u003e \u003cp\u003eGetting Started with Data Versioning 53\u003c\/p\u003e \u003cp\u003eKnowing “Just Enough” Engineering 57\u003c\/p\u003e \u003cp\u003e\u003cb\u003e4 Standing Up Your LLM 61\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eSelecting Your LLM 61\u003c\/p\u003e \u003cp\u003eWhat Type of Inference Do I Need to Perform? 65\u003c\/p\u003e \u003cp\u003eHow Open-Ended Is This Task? 66\u003c\/p\u003e \u003cp\u003eWhat Are the Privacy Concerns for This Data? 66\u003c\/p\u003e \u003cp\u003eHow Much Will This Model Cost? 67\u003c\/p\u003e \u003cp\u003eExperiment Management with LLMs 68\u003c\/p\u003e \u003cp\u003eLLM Inference 74\u003c\/p\u003e \u003cp\u003eBasics of Prompt Engineering 74\u003c\/p\u003e \u003cp\u003eIn-Context Learning 77\u003c\/p\u003e \u003cp\u003eIntermediary Computation 85\u003c\/p\u003e \u003cp\u003eAugmented Generation 89\u003c\/p\u003e \u003cp\u003eAgentic Techniques 94\u003c\/p\u003e \u003cp\u003eOptimizing LLM Inference with Experiment Management 102\u003c\/p\u003e \u003cp\u003eFine-Tuning LLMs 111\u003c\/p\u003e \u003cp\u003eWhen to Fine-Tune an LLM 112\u003c\/p\u003e \u003cp\u003eQuantization, QLOrA, and Parameter Efficient Fine-Tuning 113\u003c\/p\u003e \u003cp\u003eWrapping Things Up 121\u003c\/p\u003e \u003cp\u003e\u003cb\u003e5 Putting Together an Application 123\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003ePrototyping with Gradio 125\u003c\/p\u003e \u003cp\u003eCreating Graphics with Plotnine 128\u003c\/p\u003e \u003cp\u003eAdding the Author Selector 137\u003c\/p\u003e \u003cp\u003eAdding a Logo 138\u003c\/p\u003e \u003cp\u003eAdding a Tab 139\u003c\/p\u003e \u003cp\u003eAdding a Title and Subtitle 140\u003c\/p\u003e \u003cp\u003eChanging the Color of the Buttons 140\u003c\/p\u003e \u003cp\u003eClick to Download Button 141\u003c\/p\u003e \u003cp\u003ePutting It All Together 141\u003c\/p\u003e \u003cp\u003eDeploying Models as APIs 144\u003c\/p\u003e \u003cp\u003eImplementing an API with FastAPI 146\u003c\/p\u003e \u003cp\u003eImplementing Uvicorn 148\u003c\/p\u003e \u003cp\u003eMonitoring an LLM 149\u003c\/p\u003e \u003cp\u003eDockerizing Your Service 151\u003c\/p\u003e \u003cp\u003eDeploying Your Own LLM 154\u003c\/p\u003e \u003cp\u003eWrapping Things Up 159\u003c\/p\u003e \u003cp\u003e\u003cb\u003e6 Rounding Out the ML Life Cycle 161\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eDeploying a Simple Random Forest Model 161\u003c\/p\u003e \u003cp\u003eAn Introduction to Model Monitoring 167\u003c\/p\u003e \u003cp\u003eModel Monitoring with Evidently AI 175\u003c\/p\u003e \u003cp\u003eBuilding a Model Monitoring System 176\u003c\/p\u003e \u003cp\u003eFinal Thoughts on Monitoring 187\u003c\/p\u003e \u003cp\u003e\u003cb\u003e7 Review of Best Practices 189\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eStep 1: Understand the Problem 189\u003c\/p\u003e \u003cp\u003eStep 2: Model Selection and Training 190\u003c\/p\u003e \u003cp\u003eStep 3: Deploy and Maintain 192\u003c\/p\u003e \u003cp\u003eStep 4: Collaborate and Communicate 196\u003c\/p\u003e \u003cp\u003eEmerging Trends in LLMs 197\u003c\/p\u003e \u003cp\u003eNext Steps in Learning 199\u003c\/p\u003e \u003cp\u003eAppendix: Additional LLM Example 201\u003c\/p\u003e \u003cp\u003eIndex 209\u003c\/p\u003e  \u003cp\u003e\u003cb\u003eKristen Kehrer\u003c\/b\u003e has been providing innovative and practical statistical modeling solutions since 2010. In 2018, she achieved recognition as a LinkedIn Top Voice in Data Science \u0026amp; Analytics. Kristen is also the founder of Data Moves Me, LLC. \u003c\/p\u003e\u003cp\u003e\u003cb\u003eCaleb Kaiser\u003c\/b\u003e is a Full Stack Engineer at Comet. Caleb was previously on the Founding Team at Cortex Labs. Caleb also worked at Scribe Media on the Author Platform Team.   \u003c\/p\u003e\u003cp\u003e\u003cb\u003eAn end-to-end framework for developing Large Language Model (LLM)-based applications\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003eTraditionally, there has been a divide between data scientists and software engineers. With the advent of LLMs, however, this has changed. Machine learning is no longer primarily a tool for data analysis, but is now a fundamental feature of modern software applications. In \u003ci\u003eMachine Learning Upgrade\u003c\/i\u003e, data scientists are given a comprehensive framework not just for understanding LLMs, but for building efficient, reproducible, and scalable LLM applications. \u003c\/p\u003e\u003cp\u003eWritten by leading data scientists, this book brings you up to date on the current state of LLM technology and offers both a conceptual and hands-on overview of how it can be most responsibly integrated into business. Readers will follow along as the authors build an LLM-powered application, providing a concrete example of their framework in action. Best practices for data versioning, experiment tracking, model monitoring, and ethical considerations are also central. \u003c\/p\u003e\u003cp\u003eData professionals of all levels looking for a holistic understanding of LLM aplications using the latest technologies and practices will benefit from this book. By adopting a data-centric view, we can identify opportunities to integrate LLMs and drive business success.\u003c\/p\u003e","brand":"Wiley","offers":[{"title":"Default Title","offer_id":47989549236453,"sku":"NP9781394249633","price":40.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1842\/7735\/files\/9781394249633.jpg?v=1761784555","url":"https:\/\/k12savings.com\/products\/machine-learning-upgrade-isbn-9781394249633","provider":"K12savings","version":"1.0","type":"link"}