Building Machine Learning and Deep Learning Models on Google Cloud Platform : A Comprehensive Guide for Beginners

Take a systematic approach to understanding the fundamentals of machine learning and deep learning from the ground up and how they are applied in practice. You will use this comprehensive guide for building and deploying learning models to address complex use cases while leveraging the computational resources of Google Cloud Platform. Author Ekaba Bisong shows you how machine learning tools and techniques are used to predict or classify events based on a set of interactions between variables known as features or attributes in a particular dataset. He teaches you how deep learning extends the machine learning algorithm of neural networks to learn complex tasks that are difficult for computers to perform, such as recognizing faces and understanding languages. And you will know how to leverage cloud computing to accelerate data science and machine learning deployments. **__Building Machine Learning and Deep Learning Models on Google Cloud Platform__** is divided into eight parts that cover the fundamentals of machine learning and deep learning, the concept of data science and cloud services, programming for data science using the Python stack, Google Cloud Platform (GCP) infrastructure and products, advanced analytics on GCP, and deploying end-to-end machine learning solution pipelines on GCP. **What You’ll Learn** * Understand the principles and fundamentals of machine learning and deep learning, the algorithms, how to use them, when to use them, and how to interpret your results * Know the programming concepts relevant to machine and deep learning design and development using the Python stack * Build and interpret machine and deep learning models * Use Google Cloud Platform tools and services to develop and deploy large-scale machine learning and deep learning products * Be aware of the different facets and design choices to consider when modeling a learning problem * Productionalize machine learning models into software products **Who This Book Is For** Beginners to the practice of data science and applied machine learning, data scientists at all levels, machine learning engineers, Google Cloud Platform data engineers/architects, and software developers Front Matter ....Pages i-xxix Front Matter ....Pages 1-1 What Is Cloud Computing? (Ekaba Bisong)....Pages 3-6 An Overview of Google Cloud Platform Services (Ekaba Bisong)....Pages 7-10 The Google Cloud SDK and Web CLI (Ekaba Bisong)....Pages 11-24 Google Cloud Storage (GCS) (Ekaba Bisong)....Pages 25-33 Google Compute Engine (GCE) (Ekaba Bisong)....Pages 35-48 JupyterLab Notebooks (Ekaba Bisong)....Pages 49-57 Google Colaboratory (Ekaba Bisong)....Pages 59-64 Front Matter ....Pages 65-65 What Is Data Science? (Ekaba Bisong)....Pages 67-70 Python (Ekaba Bisong)....Pages 71-89 NumPy (Ekaba Bisong)....Pages 91-113 Pandas (Ekaba Bisong)....Pages 115-150 Matplotlib and Seaborn (Ekaba Bisong)....Pages 151-165 Front Matter ....Pages 167-167 What Is Machine Learning? (Ekaba Bisong)....Pages 169-170 Principles of Learning (Ekaba Bisong)....Pages 171-197 Batch vs. Online Learning (Ekaba Bisong)....Pages 199-201 Optimization for Machine Learning: Gradient Descent (Ekaba Bisong)....Pages 203-207 Learning Algorithms (Ekaba Bisong)....Pages 209-211 Front Matter ....Pages 213-213 Introduction to Scikit-learn (Ekaba Bisong)....Pages 215-229 Linear Regression (Ekaba Bisong)....Pages 231-241 Logistic Regression (Ekaba Bisong)....Pages 243-250 Regularization for Linear Models (Ekaba Bisong)....Pages 251-254 Support Vector Machines (Ekaba Bisong)....Pages 255-268 Ensemble Methods (Ekaba Bisong)....Pages 269-286 More Supervised Machine Learning Techniques with Scikit-learn (Ekaba Bisong)....Pages 287-308 Clustering (Ekaba Bisong)....Pages 309-318 Principal Component Analysis (PCA) (Ekaba Bisong)....Pages 319-324 Front Matter ....Pages 325-325 What Is Deep Learning? (Ekaba Bisong)....Pages 327-329 Neural Network Foundations (Ekaba Bisong)....Pages 331-332 Training a Neural Network (Ekaba Bisong)....Pages 333-343 Front Matter ....Pages 345-345 TensorFlow 2.0 and Keras (Ekaba Bisong)....Pages 347-399 The Multilayer Perceptron (MLP) (Ekaba Bisong)....Pages 401-405 Other Considerations for Training the Network (Ekaba Bisong)....Pages 407-410 More on Optimization Techniques (Ekaba Bisong)....Pages 411-413 Regularization for Deep Learning (Ekaba Bisong)....Pages 415-421 Convolutional Neural Networks (CNN) (Ekaba Bisong)....Pages 423-441 Recurrent Neural Networks (RNNs) (Ekaba Bisong)....Pages 443-473 Autoencoders (Ekaba Bisong)....Pages 475-482 Front Matter ....Pages 483-483 Google BigQuery (Ekaba Bisong)....Pages 485-517 Google Cloud Dataprep (Ekaba Bisong)....Pages 519-535 Google Cloud Dataflow (Ekaba Bisong)....Pages 537-543 Google Cloud Machine Learning Engine (Cloud MLE) (Ekaba Bisong)....Pages 545-579 Google AutoML: Cloud Vision (Ekaba Bisong)....Pages 581-598 Google AutoML: Cloud Natural Language Processing (Ekaba Bisong)....Pages 599-612 Model to Predict the Critical Temperature of Superconductors (Ekaba Bisong)....Pages 613-652 Front Matter ....Pages 653-653 Containers and Google Kubernetes Engine (Ekaba Bisong)....Pages 655-670 Kubeflow and Kubeflow Pipelines (Ekaba Bisong)....Pages 671-685 Deploying an End-to-End Machine Learning Solution on Kubeflow Pipelines (Ekaba Bisong)....Pages 687-695 Back Matter ....Pages 697-709 Take a systematic approach to understanding the fundamentals of machine learning and deep learning from the ground up and how they are applied in practice. You will use this comprehensive guide for building and deploying learning models to address complex use cases while leveraging the computational resources of Google Cloud Platform. Author Ekaba Bisong shows you how machine learning tools and techniques are used to predict or classify events based on a set of interactions between variables known as features or attributes in a particular dataset. He teaches you how deep learning extends the machine learning algorithm of neural networks to learn complex tasks that are difficult for computers to perform, such as recognizing faces and understanding languages. And you will know how to leverage cloud computing to accelerate data science and machine learning deployments. Building Machine Learning and Deep Learning Models on Google Cloud Platform is divided into eight parts that cover the fundamentals of machine learning and deep learning, the concept of data science and cloud services, programming for data science using the Python stack, Google Cloud Platform (GCP) infrastructure and products, advanced analytics on GCP, and deploying end-to-end machine learning solution pipelines on GCP. You will: Understand the principles and fundamentals of machine learning and deep learning, the algorithms, how to use them, when to use them, and how to interpret your results Know the programming concepts relevant to machine and deep learning design and development using the Python stack Build and interpret machine and deep learning models Use Google Cloud Platform tools and services to develop and deploy large-scale machine learning and deep learning products Be aware of the different facets and design choices to consider when modeling a learning problem Productionalize machine learning models into software products