{"product_id":"introducing-machine-learning-9780135565667","title":"Introducing Machine Learning","description":"\u003cb\u003eBook Synopsis\u003c\/b\u003e\u003cbr\u003e\u003cp\u003e\u003cstrong\u003eDino Esposito:\u003c\/strong\u003e If I look back, I count more 20 books authored and 1000+ articles in a 25-year-long career. I've been writing the Cutting Edge column for MSDN Magazine month after month for 22 consecutive years. It is commonly recognized that such books and articles have helped the professional growth of thousands of .NET and ASP.NET developers and software architects worldwide.\u003c\/p\u003e \u003cp\u003eAfter I escaped a dreadful COBOL project, in 1992 I started as a C developer, and since then, I have witnessed MFC and ATL, COM and DCOM, the debut of .NET, the rise and fall of Silverlight, and the ups and downs of various architectural patterns. In 1995 I led a team of five dreamers who actually deployed things that today we would call Google Photos and Shuttershockdesktop applications capable of dealing with photos stored in a virtual place that nobody had called the cloud yet. Since 2003 I have written Microsoft Press books about ASP.NET and also authored the bestseller \u003cem\u003eMicroso\u003cbr\u003e\u003cbr\u003e\u003cb\u003eTable of Contents\u003c\/b\u003e\u003cbr\u003e\u003cp\u003e Introduction\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003ePart I Laying the Groundwork of Machine Learning\u003c\/strong\u003e\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 1\u003c\/strong\u003e How Humans Learn\u003c\/p\u003e \u003cp\u003eThe Journey Toward Thinking Machines\u003c\/p\u003e \u003cp\u003e The Dawn of Mechanical Reasoning\u003c\/p\u003e \u003cp\u003e Godel’s Incompleteness Theorems\u003c\/p\u003e \u003cp\u003e Formalization of Computing Machines\u003c\/p\u003e \u003cp\u003e Toward the Formalization of Human Thought\u003c\/p\u003e \u003cp\u003e The Birth of Artificial Intelligence as a Discipline\u003c\/p\u003e \u003cp\u003eThe Biology of Learning\u003c\/p\u003e \u003cp\u003e What Is Intelligent Software, Anyway?\u003c\/p\u003e \u003cp\u003e How Neurons Work\u003c\/p\u003e \u003cp\u003e The Carrot-and-Stick Approach\u003c\/p\u003e \u003cp\u003e Adaptability to Changes\u003c\/p\u003e \u003cp\u003eArtificial Forms of Intelligence\u003c\/p\u003e \u003cp\u003e Primordial Intelligence\u003c\/p\u003e \u003cp\u003e Expert Systems\u003c\/p\u003e \u003cp\u003e Autonomous Systems\u003c\/p\u003e \u003cp\u003e Artificial Forms of Sentiment\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 2\u003c\/strong\u003e Intelligent Software\u003c\/p\u003e \u003cp\u003eApplied Artificial Intelligence\u003c\/p\u003e \u003cp\u003e Evolution of Software Intelligence\u003c\/p\u003e \u003cp\u003e Expert Systems\u003c\/p\u003e \u003cp\u003eGeneral Artificial Intelligence\u003c\/p\u003e \u003cp\u003e Unsupervised Learning\u003c\/p\u003e \u003cp\u003e Supervised Learning\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 3\u003c\/strong\u003e Mapping Problems and Algorithms\u003c\/p\u003e \u003cp\u003eFundamental Problems\u003c\/p\u003e \u003cp\u003e Classifying Objects\u003c\/p\u003e \u003cp\u003e Predicting Results\u003c\/p\u003e \u003cp\u003e Grouping Objects\u003c\/p\u003e \u003cp\u003eMore Complex Problems\u003c\/p\u003e \u003cp\u003e Image Classification\u003c\/p\u003e \u003cp\u003e Object Detection\u003c\/p\u003e \u003cp\u003e Text Analytics\u003c\/p\u003e \u003cp\u003eAutomated Machine Learning\u003c\/p\u003e \u003cp\u003e Aspects of an AutoML Platform\u003c\/p\u003e \u003cp\u003e The AutoML Model Builder in Action\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 4\u003c\/strong\u003e General Steps for a Machine Learning Solution\u003c\/p\u003e \u003cp\u003eData Collection\u003c\/p\u003e \u003cp\u003e Data-Driven Culture in the Organization\u003c\/p\u003e \u003cp\u003e Storage Options\u003c\/p\u003e \u003cp\u003eData Preparation\u003c\/p\u003e \u003cp\u003e Improving Data Quality\u003c\/p\u003e \u003cp\u003e Cleaning Data\u003c\/p\u003e \u003cp\u003e Feature Engineering\u003c\/p\u003e \u003cp\u003e Finalizing the Training Dataset\u003c\/p\u003e \u003cp\u003eModel Selection and Training\u003c\/p\u003e \u003cp\u003e The Algorithm Cheat Sheet\u003c\/p\u003e \u003cp\u003e The Case for Neural Networks\u003c\/p\u003e \u003cp\u003e Evaluation of the Model Performance\u003c\/p\u003e \u003cp\u003eDeployment of the Model\u003c\/p\u003e \u003cp\u003e Choosing the Appropriate Hosting Platform\u003c\/p\u003e \u003cp\u003e Exposing an API\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 5\u003c\/strong\u003e The Data Factor\u003c\/p\u003e \u003cp\u003eData Quality\u003c\/p\u003e \u003cp\u003e Data Validity\u003c\/p\u003e \u003cp\u003e Data Collection\u003c\/p\u003e \u003cp\u003eData Integrity\u003c\/p\u003e \u003cp\u003e Completeness\u003c\/p\u003e \u003cp\u003e Uniqueness\u003c\/p\u003e \u003cp\u003e Timeliness\u003c\/p\u003e \u003cp\u003e Accuracy\u003c\/p\u003e \u003cp\u003e Consistency\u003c\/p\u003e \u003cp\u003eWhat’s a Data Scientist, Anyway?\u003c\/p\u003e \u003cp\u003e The Data Scientist at Work\u003c\/p\u003e \u003cp\u003e The Data Scientist Tool Chest\u003c\/p\u003e \u003cp\u003e Data Scientists and Software Developers\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003ePart II Machine Learning In .NET\u003c\/strong\u003e\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 6\u003c\/strong\u003e The .NET Way\u003c\/p\u003e \u003cp\u003eWhy (Not) Python?\u003c\/p\u003e \u003cp\u003e Why Is Python So Popular in Machine Learning?\u003c\/p\u003e \u003cp\u003e Taxonomy of Python Machine Learning Libraries\u003c\/p\u003e \u003cp\u003e End-to-End Solutions on Top of Python Models\u003c\/p\u003e \u003cp\u003eIntroducing ML.NET\u003c\/p\u003e \u003cp\u003e Creating and Consuming Models in ML.NET\u003c\/p\u003e \u003cp\u003e Elements of the Learning Context\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 7\u003c\/strong\u003e Implementing the ML.NET Pipeline\u003c\/p\u003e \u003cp\u003eThe Data to Start From\u003c\/p\u003e \u003cp\u003e Exploring the Dataset\u003c\/p\u003e \u003cp\u003e Applying Common Data Transformations\u003c\/p\u003e \u003cp\u003e Considerations on the Dataset\u003c\/p\u003e \u003cp\u003eThe Training Step\u003c\/p\u003e \u003cp\u003e Picking an Algorithm\u003c\/p\u003e \u003cp\u003e Measuring the Actual Value of an Algorithm\u003c\/p\u003e \u003cp\u003e Planning the Testing Phase\u003c\/p\u003e \u003cp\u003e A Look at the Metrics\u003c\/p\u003e \u003cp\u003ePrice Prediction from Within a Client Application\u003c\/p\u003e \u003cp\u003e Getting the Model File\u003c\/p\u003e \u003cp\u003e Setting Up the ASP.NET Application\u003c\/p\u003e \u003cp\u003e Making a Taxi Fare Prediction\u003c\/p\u003e \u003cp\u003e Devising an Adequate User Interface\u003c\/p\u003e \u003cp\u003e Questioning Data and Approach to the Problem\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 8\u003c\/strong\u003e ML.NET Tasks and Algorithms\u003c\/p\u003e \u003cp\u003eThe Overall ML.NET Architecture\u003c\/p\u003e \u003cp\u003e Involved Types and Interfaces\u003c\/p\u003e \u003cp\u003e Data Representation\u003c\/p\u003e \u003cp\u003e Supported Catalogs\u003c\/p\u003e \u003cp\u003eClassification Tasks\u003c\/p\u003e \u003cp\u003e Binary Classification\u003c\/p\u003e \u003cp\u003e Multiclass Classification\u003c\/p\u003e \u003cp\u003eClustering Tasks\u003c\/p\u003e \u003cp\u003e Preparing Data for Work\u003c\/p\u003e \u003cp\u003e Training the Model\u003c\/p\u003e \u003cp\u003e Evaluating the Model\u003c\/p\u003e \u003cp\u003eTransfer Learning\u003c\/p\u003e \u003cp\u003e Steps for Building an Image Classifier\u003c\/p\u003e \u003cp\u003e Applying Necessary Data Transformations\u003c\/p\u003e \u003cp\u003e Composing and Training the Model\u003c\/p\u003e \u003cp\u003e Margin Notes on Transfer Learning\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003ePart III Fundamentals of Shallow Learning\u003c\/strong\u003e\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 9\u003c\/strong\u003e Math Foundations of Machine Learning\u003c\/p\u003e \u003cp\u003eUnder the Umbrella of Statistics\u003c\/p\u003e \u003cp\u003e The Mean in Statistics\u003c\/p\u003e \u003cp\u003e The Mode in Statistics\u003c\/p\u003e \u003cp\u003e The Median in Statistics\u003c\/p\u003e \u003cp\u003eBias and Variance\u003c\/p\u003e \u003cp\u003e The Variance in Statistics\u003c\/p\u003e \u003cp\u003e The Bias in Statistics\u003c\/p\u003e \u003cp\u003eData Representation\u003c\/p\u003e \u003cp\u003e Five-number Summary\u003c\/p\u003e \u003cp\u003e Histograms\u003c\/p\u003e \u003cp\u003e Scatter Plots\u003c\/p\u003e \u003cp\u003e Scatter Plot Matrices\u003c\/p\u003e \u003cp\u003e Plotting at the Appropriate Scale\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 10\u003c\/strong\u003e Metrics of Machine Learning\u003c\/p\u003e \u003cp\u003eStatistics vs. Machine Learning\u003c\/p\u003e \u003cp\u003e The Ultimate Goal of Machine Learning\u003c\/p\u003e \u003cp\u003e From Statistical Models to Machine Learning Models\u003c\/p\u003e \u003cp\u003eEvaluation of a Machine Learning Model\u003c\/p\u003e \u003cp\u003e From Dataset to Predictions\u003c\/p\u003e \u003cp\u003e Measuring the Precision of a Model\u003c\/p\u003e \u003cp\u003ePreparing Data for Processing\u003c\/p\u003e \u003cp\u003e Scaling\u003c\/p\u003e \u003cp\u003e Standardization\u003c\/p\u003e \u003cp\u003e Normalization\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 11\u003c\/strong\u003e How to Make Simple Predictions: Linear Regression\u003c\/p\u003e \u003cp\u003eThe Problem\u003c\/p\u003e \u003cp\u003e Guessing Results Guided by Data\u003c\/p\u003e \u003cp\u003e Making Hypotheses About the Relationship\u003c\/p\u003e \u003cp\u003eThe Linear Algorithm\u003c\/p\u003e \u003cp\u003e The General Idea\u003c\/p\u003e \u003cp\u003e Identifying the Cost Function\u003c\/p\u003e \u003cp\u003e The Ordinary Least Square Algorithm\u003c\/p\u003e \u003cp\u003e The Gradient Descent Algorithm\u003c\/p\u003e \u003cp\u003e How Good Is the Algorithm?\u003c\/p\u003e \u003cp\u003eImproving the Solution\u003c\/p\u003e \u003cp\u003e The Polynomial Route\u003c\/p\u003e \u003cp\u003e Regularization\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 12\u003c\/strong\u003e How to Make Complex Predictions and Decisions: Trees\u003c\/p\u003e \u003cp\u003eThe Problem\u003c\/p\u003e \u003cp\u003e What’s a Tree, Anyway?\u003c\/p\u003e \u003cp\u003e Trees in Machine Learning\u003c\/p\u003e \u003cp\u003e A Sample Tree-Based Algorithm\u003c\/p\u003e \u003cp\u003eDesign Principles for Tree-Based Algorithms\u003c\/p\u003e \u003cp\u003e Decision Trees versus Expert Systems\u003c\/p\u003e \u003cp\u003e Flavors of Tree Algorithms\u003c\/p\u003e \u003cp\u003eClassification Trees\u003c\/p\u003e \u003cp\u003e How the CART Algorithm Works\u003c\/p\u003e \u003cp\u003e How the ID3 Algorithm Works\u003c\/p\u003e \u003cp\u003eRegression Trees\u003c\/p\u003e \u003cp\u003e How the Algorithm Works\u003c\/p\u003e \u003cp\u003e Tree Pruning\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 13\u003c\/strong\u003e How to Make Better Decisions: Ensemble Methods\u003c\/p\u003e \u003cp\u003eThe Problem\u003c\/p\u003e \u003cp\u003eThe Bagging Technique\u003c\/p\u003e \u003cp\u003e Random Forest Algorithms\u003c\/p\u003e \u003cp\u003e Steps of the Algorithms\u003c\/p\u003e \u003cp\u003e Pros and Cons\u003c\/p\u003e \u003cp\u003eThe Boosting Technique\u003c\/p\u003e \u003cp\u003e The Power of Boosting\u003c\/p\u003e \u003cp\u003e Gradient Boosting\u003c\/p\u003e \u003cp\u003e Pros and Cons\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 14\u003c\/strong\u003e Probabilistic Methods: Naïve Bayes\u003c\/p\u003e \u003cp\u003eQuick Introduction to Bayesian Statistics\u003c\/p\u003e \u003cp\u003e Introducing Bayesian Probability\u003c\/p\u003e \u003cp\u003e Some Preliminary Notation\u003c\/p\u003e \u003cp\u003e Bayes’ Theorem\u003c\/p\u003e \u003cp\u003e A Practical Code Review Example\u003c\/p\u003e \u003cp\u003eApplying Bayesian Statistics to Classification\u003c\/p\u003e \u003cp\u003e Initial Formulation of the Problem\u003c\/p\u003e \u003cp\u003e A Simplified (Yet Effective) Formulation\u003c\/p\u003e \u003cp\u003e Practical Aspects of Bayesian Classifiers\u003c\/p\u003e \u003cp\u003eNaïve Bayes Classifiers\u003c\/p\u003e \u003cp\u003e The General Algorithm\u003c\/p\u003e \u003cp\u003e Multinomial Naïve Bayes\u003c\/p\u003e \u003cp\u003e Bernoulli Naïve Bayes\u003c\/p\u003e \u003cp\u003e Gaussian Naïve Bayes\u003c\/p\u003e \u003cp\u003eNaïve Bayes Regression\u003c\/p\u003e \u003cp\u003e Foundation of Bayesian Linear Regression\u003c\/p\u003e \u003cp\u003e Applications of Bayesian Linear Regression\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 15\u003c\/strong\u003e How to Group Data: Classification and Clustering\u003c\/p\u003e \u003cp\u003eA Basic Approach to Supervised Classification\u003c\/p\u003e \u003cp\u003e The K-Nearest Neighbors Algorithm\u003c\/p\u003e \u003cp\u003e Steps of the Algorithm\u003c\/p\u003e \u003cp\u003e Business Scenarios\u003c\/p\u003e \u003cp\u003eSupport Vector Machine\u003c\/p\u003e \u003cp\u003e Overview of the Algorithm\u003c\/p\u003e \u003cp\u003e A Quick Mathematical Refresher\u003c\/p\u003e \u003cp\u003e Steps of the Algorithm\u003c\/p\u003e \u003cp\u003eUnsupervised Clustering\u003c\/p\u003e \u003cp\u003e A Business Case: Reducing the Dataset\u003c\/p\u003e \u003cp\u003e The K-Means Algorithm\u003c\/p\u003e \u003cp\u003e The K-Modes Algorithm\u003c\/p\u003e \u003cp\u003e The DBSCAN Algorithm\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003ePart IV Fundamentals of Deep Learning\u003c\/strong\u003e\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 16\u003c\/strong\u003e Feed-Forward Neural Networks\u003c\/p\u003e \u003cp\u003eA Brief History of Neural Networks\u003c\/p\u003e \u003cp\u003e The McCulloch-Pitt Neuron\u003c\/p\u003e \u003cp\u003e Feed-Forward Networks\u003c\/p\u003e \u003cp\u003e More Sophisticated Networks\u003c\/p\u003e \u003cp\u003eTypes of Artificial Neurons\u003c\/p\u003e \u003cp\u003e The Perceptron Neuron\u003c\/p\u003e \u003cp\u003e The Logistic Neuron\u003c\/p\u003e \u003cp\u003eTraining a Neural Network\u003c\/p\u003e \u003cp\u003e The Overall Learning Strategy\u003c\/p\u003e \u003cp\u003e The Backpropagation Algorithm\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 17\u003c\/strong\u003e Design of a Neural Network\u003c\/p\u003e \u003cp\u003eAspects of a Neural Network\u003c\/p\u003e \u003cp\u003e Activation Functions\u003c\/p\u003e \u003cp\u003e Hidden Layers\u003c\/p\u003e \u003cp\u003e The Output Layer\u003c\/p\u003e \u003cp\u003eBuilding a Neural Network\u003c\/p\u003e \u003cp\u003e Available Frameworks\u003c\/p\u003e \u003cp\u003e Your First Neural Network in Keras\u003c\/p\u003e \u003cp\u003e Neural Networks versus Other Algorithms\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 18\u003c\/strong\u003e Other Types of Neural Networks\u003c\/p\u003e \u003cp\u003eCommon Issues of Feed-Forward Neural Networks\u003c\/p\u003e \u003cp\u003eRecurrent Neural Networks\u003c\/p\u003e \u003cp\u003e Anatomy of a Stateful Neural Network\u003c\/p\u003e \u003cp\u003e LSTM Neural Networks\u003c\/p\u003e \u003cp\u003eConvolutional Neural Networks\u003c\/p\u003e \u003cp\u003e Image Classification and Recognition\u003c\/p\u003e \u003cp\u003e The Convolutional Layer\u003c\/p\u003e \u003cp\u003e The Pooling Layer\u003c\/p\u003e \u003cp\u003e The Fully Connected Layer\u003c\/p\u003e \u003cp\u003eFurther Neural Network Developments\u003c\/p\u003e \u003cp\u003e Generative Adversarial Neural Networks\u003c\/p\u003e \u003cp\u003e Auto-Encoders\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 19\u003c\/strong\u003e Sentiment Analysis: An End-to-End Solution\u003c\/p\u003e \u003cp\u003ePreparing Data for Training\u003c\/p\u003e \u003cp\u003e Formalizing the Problem\u003c\/p\u003e \u003cp\u003e Getting the Data.\u003c\/p\u003e \u003cp\u003e Manipulating the Data\u003c\/p\u003e \u003cp\u003e Considerations on the Intermediate Format\u003c\/p\u003e \u003cp\u003eTraining the Model\u003c\/p\u003e \u003cp\u003e Choosing the Ecosystem\u003c\/p\u003e \u003cp\u003e Building a Dictionary of Words\u003c\/p\u003e \u003cp\u003e Choosing the Trainer\u003c\/p\u003e \u003cp\u003e Other Aspects of the Network\u003c\/p\u003e \u003cp\u003eThe Client Application\u003c\/p\u003e \u003cp\u003e Getting Input for the Model\u003c\/p\u003e \u003cp\u003e Getting the Prediction from the Model\u003c\/p\u003e \u003cp\u003e Turning the Response into Usable Information\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003ePart V Final Thoughts\u003c\/strong\u003e\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 20 \u003c\/strong\u003eAI Cloud Services for the Real World\u003c\/p\u003e \u003cp\u003eAzure Cognitive Services\u003c\/p\u003e \u003cp\u003eAzure Machine Learning Studio\u003c\/p\u003e \u003cp\u003e Azure Machine Learning Service\u003c\/p\u003e \u003cp\u003e Data Science Virtual Machines\u003c\/p\u003e \u003cp\u003eOn-Premises Services\u003c\/p\u003e \u003cp\u003e SQL Server Machine Learning Services\u003c\/p\u003e \u003cp\u003e Machine Learning Server\u003c\/p\u003e \u003cp\u003eMicrosoft Data Processing Services\u003c\/p\u003e \u003cp\u003e Azure Data Lake\u003c\/p\u003e \u003cp\u003e Azure Databricks\u003c\/p\u003e \u003cp\u003e Azure HDInsight\u003c\/p\u003e \u003cp\u003e .NET for Apache Spark\u003c\/p\u003e \u003cp\u003e Azure Data Share\u003c\/p\u003e \u003cp\u003e Azure Data Factory\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e\u003cstrong\u003eChapter 21\u003c\/strong\u003e The Business Perception of AI\u003c\/p\u003e \u003cp\u003ePerception of AI in the Industry\u003c\/p\u003e \u003cp\u003e Realizing the Potential\u003c\/p\u003e \u003cp\u003e What Artificial Intelligence Can Do for You\u003c\/p\u003e \u003cp\u003e Challenges Around the Corner\u003c\/p\u003e \u003cp\u003eEnd-to-End Solutions\u003c\/p\u003e \u003cp\u003e Let’s Just Call It Consulting\u003c\/p\u003e \u003cp\u003e The Borderline Between Software and Data Science\u003c\/p\u003e \u003cp\u003e Agile AI\u003c\/p\u003e \u003cp\u003eSummary\u003c\/p\u003e \u003cp\u003e9780135565667 TOC 12\/19\/2019\u003c\/p\u003e\u003c\/em\u003e\u003c\/p\u003e","brand":"Pearson Education (US)","offers":[{"title":"Default Title","offer_id":49369130303831,"sku":"9780135565667","price":23.19,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0817\/1739\/5799\/files\/9780135565667.jpg?v=1730128507","url":"https:\/\/bookcurl.com\/products\/introducing-machine-learning-9780135565667","provider":"Book Curl","version":"1.0","type":"link"}