{"product_id":"keras-to-kubernetes-isbn-9781119564836","title":"Keras to Kubernetes","description":"\u003cp\u003e\u003cb\u003eBuild a Keras model to scale and deploy on a Kubernetes cluster\u003cbr\u003e\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eWe have seen an exponential growth in the use of Artificial Intelligence (AI) over last few years. AI is becoming the new electricity and is touching every industry from retail to manufacturing to healthcare to entertainment. Within AI, we�re seeing a particular growth in Machine Learning (ML) and Deep Learning (DL) applications. ML is all about learning relationships from labeled (Supervised) or unlabeled data (Unsupervised). DL has many layers of learning and can extract patterns from unstructured data like images, video, audio, etc. \u003c\/p\u003e \u003cp\u003e\u003cem style=\"box-sizing: border-box;\"\u003e\u003ci\u003eKeras to Kubernetes: The Journey of a Machine Learning Model to Production\u003c\/i\u003e takes you through real-world examples of building DL models in Keras for recognizing product logos in images and extracting sentiment from text. You will then take that trained model and package it as a web application container before learning how to deploy this model at scale on a Kubernetes cluster. You will understand the different practical steps involved in real-world ML implementations which go beyond the algorithms.\u003c\/em\u003e\u003c\/p\u003e \u003cp\u003e•    Find hands-on learning examples \u003c\/p\u003e \u003cp\u003e•    Learn to uses Keras and Kubernetes to deploy Machine Learning models\u003c\/p\u003e \u003cp\u003e•    Discover new ways to collect and manage your image and text data with Machine Learning\u003c\/p\u003e \u003cp\u003e•    Reuse examples as-is to deploy your models\u003c\/p\u003e \u003cp\u003e•    Understand the ML model development lifecycle and deployment to production\u003c\/p\u003e \u003cp\u003eIf you�re ready to learn about one of the most popular DL frameworks and build production applications with it, you�ve come to the right place!\u003c\/p\u003e \u003cp\u003eIntroduction xiii\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 1 Big Data and Artificial Intelligence 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eData Is the New Oil and AI Is the New Electricity 1\u003c\/p\u003e \u003cp\u003eRise of the Machines 4\u003c\/p\u003e \u003cp\u003eExponential Growth in Processing 4\u003c\/p\u003e \u003cp\u003eA New Breed of Analytics 5\u003c\/p\u003e \u003cp\u003eWhat Makes AI So Special 7\u003c\/p\u003e \u003cp\u003eApplications of Artificial Intelligence 8\u003c\/p\u003e \u003cp\u003eBuilding Analytics on Data 12\u003c\/p\u003e \u003cp\u003eTypes of Analytics: Based on the Application 13\u003c\/p\u003e \u003cp\u003eTypes of Analytics: Based on Decision Logic 17\u003c\/p\u003e \u003cp\u003eBuilding an Analytics-Driven System 18\u003c\/p\u003e \u003cp\u003eSummary 21\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 2 Machine Learning 23\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eFinding Patterns in Data 23\u003c\/p\u003e \u003cp\u003eThe Awesome Machine Learning Community 26\u003c\/p\u003e \u003cp\u003eTypes of Machine Learning Techniques 27\u003c\/p\u003e \u003cp\u003eUnsupervised Machine Learning 27\u003c\/p\u003e \u003cp\u003eSupervised Machine Learning 29\u003c\/p\u003e \u003cp\u003eReinforcement Learning 31\u003c\/p\u003e \u003cp\u003eSolving a Simple Problem 31\u003c\/p\u003e \u003cp\u003eUnsupervised Learning 33\u003c\/p\u003e \u003cp\u003eSupervised Learning: Linear Regression 37\u003c\/p\u003e \u003cp\u003eGradient Descent Optimization 40\u003c\/p\u003e \u003cp\u003eApplying Gradient Descent to Linear Regression 42\u003c\/p\u003e \u003cp\u003eSupervised Learning: Classification 43\u003c\/p\u003e \u003cp\u003eAnalyzing a Bigger Dataset 48\u003c\/p\u003e \u003cp\u003eMetrics for Accuracy: Precision and Recall 50\u003c\/p\u003e \u003cp\u003eComparison of Classification Methods 52\u003c\/p\u003e \u003cp\u003eBias vs. Variance: Underfitting vs. Overfitting 57\u003c\/p\u003e \u003cp\u003eReinforcement Learning 62\u003c\/p\u003e \u003cp\u003eModel-Based RL 63\u003c\/p\u003e \u003cp\u003eModel-Free RL 65\u003c\/p\u003e \u003cp\u003eSummary 70\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 3 Handling Unstructured Data 71\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eStructured vs. Unstructured Data 71\u003c\/p\u003e \u003cp\u003eMaking Sense of Images 74\u003c\/p\u003e \u003cp\u003eDealing with Videos 89\u003c\/p\u003e \u003cp\u003eHandling Textual Data 90\u003c\/p\u003e \u003cp\u003eListening to Sound 104\u003c\/p\u003e \u003cp\u003eSummary 108\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 4 Deep Learning Using Keras 111\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eHandling Unstructured Data 111\u003c\/p\u003e \u003cp\u003eNeural Networks 112\u003c\/p\u003e \u003cp\u003eBack-Propagation and Gradient Descent 117\u003c\/p\u003e \u003cp\u003eBatch vs. Stochastic Gradient Descent 119\u003c\/p\u003e \u003cp\u003eNeural Network Architectures 120\u003c\/p\u003e \u003cp\u003eWelcome to TensorFlow and Keras 121\u003c\/p\u003e \u003cp\u003eBias vs. Variance: Underfitting vs. Overfitting 126\u003c\/p\u003e \u003cp\u003eSummary 129\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 5 Advanced Deep Learning 131\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eThe Rise of Deep Learning Models 131\u003c\/p\u003e \u003cp\u003eNew Kinds of Network Layers 132\u003c\/p\u003e \u003cp\u003eConvolution Layer 133\u003c\/p\u003e \u003cp\u003ePooling Layer 135\u003c\/p\u003e \u003cp\u003eDropout Layer 135\u003c\/p\u003e \u003cp\u003eBatch Normalization Layer 135\u003c\/p\u003e \u003cp\u003eBuilding a Deep Network for Classifying Fashion Images 136\u003c\/p\u003e \u003cp\u003eCNN Architectures and Hyper-Parameters 143\u003c\/p\u003e \u003cp\u003eMaking Predictions Using a Pretrained VGG Model 145\u003c\/p\u003e \u003cp\u003eData Augmentation and Transfer Learning 149\u003c\/p\u003e \u003cp\u003eA Real Classification Problem: Pepsi vs. Coke 150\u003c\/p\u003e \u003cp\u003eRecurrent Neural Networks 160\u003c\/p\u003e \u003cp\u003eSummary 166\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 6 Cutting-Edge Deep Learning Projects 169\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eNeural Style Transfer 169\u003c\/p\u003e \u003cp\u003eGenerating Images Using AI 180\u003c\/p\u003e \u003cp\u003eCredit Card Fraud Detection with Autoencoders 188\u003c\/p\u003e \u003cp\u003eSummary 198\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 7 AI in the Modern Software World 199\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eA Quick Look at Modern Software Needs 200\u003c\/p\u003e \u003cp\u003eHow AI Fits into Modern Software Development 202\u003c\/p\u003e \u003cp\u003eSimple to Fancy Web Applications 203\u003c\/p\u003e \u003cp\u003eThe Rise of Cloud Computing 205\u003c\/p\u003e \u003cp\u003eContainers and CaaS 209\u003c\/p\u003e \u003cp\u003eMicroservices Architecture with Containers 212\u003c\/p\u003e \u003cp\u003eKubernetes: A CaaS Solution for Infrastructure Concerns 214\u003c\/p\u003e \u003cp\u003eSummary 221\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 8 Deploying AI Models as Microservices 223\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eBuilding a Simple Microservice with Docker and Kubernetes 223\u003c\/p\u003e \u003cp\u003eAdding AI Smarts to Your App 228\u003c\/p\u003e \u003cp\u003ePackaging the App as a Container 233\u003c\/p\u003e \u003cp\u003ePushing a Docker Image to a Repository 238\u003c\/p\u003e \u003cp\u003eDeploying the App on Kubernetes as a Microservice 238\u003c\/p\u003e \u003cp\u003eSummary 240\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 9 Machine Learning Development Lifecycle 243\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eMachine Learning Model Lifecycle 244\u003c\/p\u003e \u003cp\u003eStep 1: Define the Problem, Establish the Ground Truth 245\u003c\/p\u003e \u003cp\u003eStep 2: Collect, Cleanse, and Prepare the Data 246\u003c\/p\u003e \u003cp\u003eStep 3: Build and Train the Model 248\u003c\/p\u003e \u003cp\u003eStep 4: Validate the Model, Tune the Hyper-Parameters 251\u003c\/p\u003e \u003cp\u003eStep 5: Deploy to Production 252\u003c\/p\u003e \u003cp\u003eFeedback and Model Updates 253\u003c\/p\u003e \u003cp\u003eDeployment on Edge Devices 254\u003c\/p\u003e \u003cp\u003eSummary 264\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 10 A Platform for Machine Learning 265\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eMachine Learning Platform Concerns 265\u003c\/p\u003e \u003cp\u003eData Acquisition 267\u003c\/p\u003e \u003cp\u003eData Cleansing 270\u003c\/p\u003e \u003cp\u003eAnalytics User Interface 271\u003c\/p\u003e \u003cp\u003eModel Development 275\u003c\/p\u003e \u003cp\u003eTraining at Scale 277\u003c\/p\u003e \u003cp\u003eHyper-Parameter Tuning 277\u003c\/p\u003e \u003cp\u003eAutomated Deployment 279\u003c\/p\u003e \u003cp\u003eLogging and Monitoring 286\u003c\/p\u003e \u003cp\u003ePutting the ML Platform Together 287\u003c\/p\u003e \u003cp\u003eSummary 288\u003c\/p\u003e \u003cp\u003eA Final Word . . . 288\u003c\/p\u003e \u003cp\u003eAppendix A References 289\u003c\/p\u003e \u003cp\u003eIndex 295\u003c\/p\u003e  \u003cp\u003e\u003cb\u003eDATTARAJ JAGDISH RAO\u003c\/b\u003e is a Principal Architect at GE Transportation (now a part of Wabtec Corporation). He has been with GE for 19 years working for Global Research, Energy and Transportation. Currently, he leads the Artificial Intelligence (AI) strategy for the global business, which involves identifying AI-growth opportunities to drive outcomes like Predictive Maintenance, Machine Vision and Digital Twins. He is building a Kubernetes based platform that aims at bridging the gap between data science and production software. He led the Innovation team out of Bangalore that incubated video Track-inspection from idea into a commercial Product. Dattaraj has 11 patents in Machine Learning and Computer Vision.   \u003c\/p\u003e\u003cp\u003e\u003cb\u003eLEARN HOW TO BUILD A KERAS MODEL TO SCALE AND DEPLOY ON A KUBERNETES CLUSTER\u003c\/b\u003e \u003c\/p\u003e\u003cp\u003eArtificial Intelligence (AI) has, in one form or another, been in existence for over six decades. However, recent years have seen an enormous increase in the amount of collectable data and major advancements in algorithms and computer hardware. Within the realm of AI technology, Machine Learning (ML) and Deep Learning (DL) applications in particular have undergone significant growth. \u003ci\u003eKeras,\u003c\/i\u003e one of the most popular DL frameworks, can quickly describe a DL model, begin training it on data, and generate more data by modifying existing data. Kubernetes is an application engine that manages applications packaged as Containers, handling all the infrastructure constraints such as scaling, fail-over, and load balancing. With the power, flexibility, and virtually limitless applications of Keras and Kubernetes comes a caveat—they can be challenging to develop and deploy effectively without proper guidance. \u003c\/p\u003e\u003cp\u003e\u003ci\u003eKeras to Kubernetes: The Journey Of A Machine Learning Model To Production\u003c\/i\u003e offers step-by-step instructions on how to build a Keras model to scale and deploy on a Kubernetes cluster. This timely and accessible guide takes readers through the entire model-to-production process, covering topics such as model serving, scaling, load balancing, API development, Algorithm-as-a-Service (AaaS), and more. Real-world examples help readers build a Keras model for detecting logos in images, package it as a web application container, and deploy it at scale on a Kubernetes cluster. A much-needed resource for Keras and Kubernetes, this book: \u003c\/p\u003e\u003cul\u003e \u003cli\u003eOffers hands-on examples to use Keras and Kubernetes to deploy Machine Learning\u003c\/li\u003e \u003cli\u003ePresents new ways to collect and manage data\u003c\/li\u003e \u003cli\u003eIncludes overviews of various AI learning models\u003c\/li\u003e \u003cli\u003eEnables readers to re-use examples without modification to deploy models\u003c\/li\u003e \u003cli\u003eProvides clear and easy-to-follow directions\u003c\/li\u003e \u003c\/ul\u003e \u003cp\u003eWritten by a respected leader in Artificial Intelligence engineering, Keras to \u003ci\u003eKubernetes: The Journey Of A Machine Learning Model To Production\u003c\/i\u003e is an ideal book for anyone seeking to learn and apply Machine Learning to their own projects.\u003c\/p\u003e","brand":"Wiley","offers":[{"title":"Default Title","offer_id":47989496840421,"sku":"NP9781119564836","price":40.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1842\/7735\/files\/9781119564836.jpg?v=1761784341","url":"https:\/\/k12savings.com\/products\/keras-to-kubernetes-isbn-9781119564836","provider":"K12savings","version":"1.0","type":"link"}