Learn Keras for Deep Neural Networks : A Fast-Track Approach to Modern Deep Learning with Python

Learn, understand, and implement deep neural networks in a math- and programming-friendly approach using Keras and Python. The book focuses on an end-to-end approach to developing supervised learning algorithms in regression and classification with practical business-centric use-cases implemented in Keras. The overall book comprises three sections with two chapters in each section. The first section prepares you with all the necessary basics to get started in deep learning. Chapter 1 introduces you to the world of deep learning and its difference from machine learning, the choices of frameworks for deep learning, and the Keras ecosystem. You will cover a real-life business problem that can be solved by supervised learning algorithms with deep neural networks. You’ll tackle one use case for regression and another for classification leveraging popular Kaggle datasets. Later, you will see an interesting and challenging part of deep learning: hyperparameter tuning; helping you further improve your models when building robust deep learning applications. Finally, you’ll further hone your skills in deep learning and cover areas of active development and research in deep learning. At the end of __Learn Keras for Deep Neural Networks__, you will have a thorough understanding of deep learning principles and have practical hands-on experience in developing enterprise-grade deep learning solutions in Keras. **What You’ll Learn** * Master fast-paced practical deep learning concepts with math- and programming-friendly abstractions. * Design, develop, train, validate, and deploy deep neural networks using the Keras framework * Use best practices for debugging and validating deep learning models * Deploy and integrate deep learning as a service into a larger software service or product * Extend deep learning principles into other popular frameworks **Who This Book Is For** Software engineers and data engineers with basic programming skills in any language and who are keen on exploring deep learning for a career move or an enterprise project. Table of Contents 4 About the Author 8 About the Technical Reviewer 9 Acknowledgments 10 Introduction 11 Chapter 1: An Introduction to Deep Learning and Keras 14 Introduction to DL 14 Demystifying the Buzzwords 15 What Are Some Classic Problems Solved by DL in Today’s Market? 18 Decomposing a DL Model 18 Exploring the Popular DL Frameworks 21 Low-Level DL Frameworks 22 Theano 22 Torch 23 PyTorch 23 MxNet 23 TensorFlow 24 High-Level DL Frameworks 24 A Sneak Peek into the Keras Framework 26 Getting the Data Ready 28 Defining the Model Structure 28 Training the Model and Making Predictions 28 Summary 29 Chapter 2: Keras in Action 30 Setting Up the Environment 30 Selecting the Python Version 30 Installing Python for Windows, Linux, or macOS 31 Installing Keras and TensorFlow Back End 32 Getting Started with DL in Keras 34 Input Data 34 Neuron 36 Activation Function 37 Sigmoid Activation Function 38 ReLU Activation Function 39 Model 41 Layers 41 Core Layers 42 Dense Layer 42 Dropout Layer 43 Other Important Layers 44 The Loss Function 45 Optimizers 48 Stochastic Gradient Descent (SGD) 50 Adam 50 Other Important Optimizers 51 Metrics 52 Model Configuration 52 Model Training 53 Model Evaluation 56 Putting All the Building Blocks Together 58 Summary 65 Chapter 3: Deep Neural Networks for Supervised Learning: Regression 66 Getting Started 66 Problem Statement 68 Why Is Representing a Problem Statement with a Design Principle Important? 69 Designing an SCQ 70 Designing the Solution 72 Exploring the Data 73 Looking at the Data Dictionary 76 Finding Data Types 79 Working with Time 80 Predicting Sales 82 Exploring Numeric Columns 83 Understanding the Categorical Features 87 Data Engineering 91 Defining Model Baseline Performance 97 Designing the DNN 98 Testing the Model Performance 102 Improving the Model 102 Increasing the Number of Neurons 106 Plotting the Loss Metric Across Epochs 110 Testing the Model Manually 111 Summary 112 Chapter 4: Deep Neural Networks for Supervised Learning: Classification 113 Getting Started 113 Problem Statement 114 Designing the SCQ 115 Designing the Solution 115 How Can We Identify a Potential Customer? 116 Exploring the Data 116 Data Engineering 122 Defining Model Baseline Accuracy 130 Designing the DNN for Classification 131 Revisiting the Data 136 Standardize, Normalize, or Scale the Data 136 Transforming the Input Data 138 DNNs for Classification with Improved Data 139 Summary 146 Chapter 5: Tuning and Deploying Deep Neural Networks 148 The Problem of Overfitting 148 So, What Is Regularization? 150 L1 Regularization 151 L2 Regularization 151 Dropout Regularization 152 Hyperparameter Tuning 153 Hyperparameters in DL 154 Number of Neurons in a Layer 154 Number of Layers 155 Number of Epochs 156 Weight Initialization 156 Batch Size 157 Learning Rate 157 Activation Function 158 Optimization 158 Approaches for Hyperparameter Tuning 158 Manual Search 159 Grid Search 159 Random Search 162 Further Reading 162 Model Deployment 163 Tailoring the Test Data 163 Saving Models to Memory 165 Retraining the Models with New Data 166 Online Models 167 Delivering Your Model As an API 168 Putting All the Pieces of the Puzzle Together 169 Summary 170 Chapter 6: The Path Ahead 171 What’s Next for DL Expertise? 171 CNN 172 RNN 177 CNN + RNN 180 Why Do We Need GPU for DL? 181 Other Hot Areas in DL (GAN) 184 Concluding Thoughts 186 Index 187 Learn, understand, and implement deep neural networks in a math- and programming-friendly approach using Keras and Python. The book focuses on an end-to-end approach to developing supervised learning algorithms in regression and classification with practical business-centric use-cases implemented in Keras. The overall book comprises three sections with two chapters in each section. The first section prepares you with all the necessary basics to get started in deep learning. Chapter 1 introduces you to the world of deep learning and its difference from machine learning, the choices of frameworks for deep learning, and the Keras ecosystem. You will cover a real-life business problem that can be solved by supervised learning algorithms with deep neural networks. You'll tackle one use case for regression and another for classification leveraging popular Kaggle datasets. Later, you will see an interesting and challenging part of deep learning: hyperparameter tuning; helping you further improve your models when building robust deep learning applications. Finally, you'll further hone your skills in deep learning and cover areas of active development and research in deep learning. At the end of Learn Keras for Deep Neural Networks, you will have a thorough understanding of deep learning principles and have practical hands-on experience in developing enterprise-grade deep learning solutions in Keras. You will: Master fast-paced practical deep learning concepts with math- and programming-friendly abstractions. Design, develop, train, validate, and deploy deep neural networks using the Keras framework Use best practices for debugging and validating deep learning models Deploy and integrate deep learning as a service into a larger software service or product Extend deep learning principles into other popular frameworks Front Matter ....Pages i-xv An Introduction to Deep Learning and Keras (Jojo Moolayil)....Pages 1-16 Keras in Action (Jojo Moolayil)....Pages 17-52 Deep Neural Networks for Supervised Learning: Regression (Jojo Moolayil)....Pages 53-99 Deep Neural Networks for Supervised Learning: Classification (Jojo Moolayil)....Pages 101-135 Tuning and Deploying Deep Neural Networks (Jojo Moolayil)....Pages 137-159 The Path Ahead (Jojo Moolayil)....Pages 161-176 Back Matter ....Pages 177-182