TensorFlow For Dummies

Table of contents

1. Cover
2. Introduction
   1. About This Book
   2. Foolish Assumptions
   3. Icons Used in this Book
   4. Beyond the Book
   5. Where to Go from Here
3. Part 1: Getting to Know TensorFlow
   1. Chapter 1: Introducing Machine Learning with TensorFlow
      1. Understanding Machine Learning
      2. The Development of Machine Learning
      3. Machine Learning Frameworks
   2. Chapter 2: Getting Your Feet Wet
      1. Installing TensorFlow
      2. Exploring the TensorFlow Installation
      3. Running Your First Application
      4. Setting the Style
   3. Chapter 3: Creating Tensors and Operations
      1. Creating Tensors
      2. Creating Tensors with Known Values
      3. Creating Tensors with Random Values
      4. Transforming Tensors
      5. Creating Operations
      6. Putting Theory into Practice
   4. Chapter 4: Executing Graphs in Sessions
      1. Forming Graphs
      2. Creating and Running Sessions
      3. Writing Messages to the Log
      4. Visualizing Data with TensorBoard
      5. Putting Theory into Practice
   5. Chapter 5: Training
      1. Training in TensorFlow
      2. Formulating the Model
      3. Looking at Variables
      4. Determining Loss
      5. Minimizing Loss with Optimization
      6. Feeding Data into a Session
      7. Monitoring Steps, Global Steps, and Epochs
      8. Saving and Restoring Variables
      9. Working with SavedModels
      10. Putting Theory into Practice
      11. Visualizing the Training Process
      12. Session Hooks
4. Part 2: Implementing Machine Learning
   1. Chapter 6: Analyzing Data with Statistical Regression
      1. Analyzing Systems Using Regression
      2. Linear Regression: Fitting Lines to Data
      3. Polynomial Regression: Fitting Polynomials to Data
      4. Binary Logistic Regression: Classifying Data into Two Categories
      5. Multinomial Logistic Regression: Classifying Data into Multiple Categories
   2. Chapter 7: Introducing Neural Networks and Deep Learning
      1. From Neurons to Perceptrons
      2. Improving the Model
      3. Layers and Deep Learning
      4. Training with Backpropagation
      5. Implementing Deep Learning
      6. Tuning the Neural Network
      7. Managing Variables with Scope
      8. Improving the Deep Learning Process
   3. Chapter 8: Classifying Images with Convolutional Neural Networks (CNNs)
      1. Filtering Images
      2. Convolutional Neural Networks (CNNs)
      3. Putting Theory into Practice
      4. Performing Image Operations
      5. Putting Theory into Practice
   4. Chapter 9: Analyzing Sequential Data with Recurrent Neural Networks (RNNs)
      1. Recurrent Neural Networks (RNNs)
      2. Creating RNN Cells
      3. Long Short-Term Memory (LSTM) Cells
      4. Gated Recurrent Units (GRUs)
5. Part 3: Simplifying and Accelerating TensorFlow
   1. Chapter 10: Accessing Data with Datasets and Iterators
      1. Datasets
      2. Iterators
      3. Putting Theory into Practice
      4. Bizarro Datasets
   2. Chapter 11: Using Threads, Devices, and Clusters
      1. Executing with Multiple Threads
      2. Configuring Devices
      3. Executing TensorFlow in a Cluster
   3. Chapter 12: Developing Applications with Estimators
      1. Introducing Estimators
      2. Training an Estimator
      3. Testing an Estimator
      4. Running an Estimator
      5. Creating Input Functions
      6. Using Feature Columns
      7. Creating and Using Estimators
      8. Running Estimators in a Cluster
      9. Accessing Experiments
   4. Chapter 13: Running Applications on the Google Cloud Platform (GCP)
      1. Overview
      2. Working with GCP Projects
      3. The Cloud Software Development Kit (SDK)
      4. The gcloud Utility
      5. Google Cloud Storage
      6. Preparing for Deployment
      7. Executing Applications with the Cloud SDK
      8. Configuring a Cluster in the Cloud
6. Part 4: The Part of Tens
   1. Chapter 14: The Ten Most Important Classes
      1. Tensor
      2. Operation
      3. Graph
      4. Session
      5. Variable
      6. Optimizer
      7. Estimator
      8. Dataset
      9. Iterator
      10. Saver
   2. Chapter 15: Ten Recommendations for Training Neural Networks
      1. Select a Representative Dataset
      2. Standardize Your Data
      3. Use Proper Weight Initialization
      4. Start with a Small Number of Layers
      5. Add Dropout Layers
      6. Train with Small, Random Batches
      7. Normalize Batch Data
      8. Try Different Optimization Algorithms
      9. Set the Right Learning Rate
      10. Check Weights and Gradients
7. About the Author
8. Advertisement Page
9. Connect with Dummies
10. Index
11. End User License Agreement