Hands-On Deep Learning with TensorFlow

Book description

This book is your guide to exploring the possibilities in the field of deep learning, making use of Google's TensorFlow. You will learn about convolutional neural networks, and logistic regression while training models for deep learning to gain key insights into your data.

About This Book

  • Explore various possibilities with deep learning and gain amazing insights from data using Google’s brainchild-- TensorFlow

  • Want to learn what more can be done with deep learning? Explore various neural networks with the help of this comprehensive guide

  • Rich in concepts, advanced guide on deep learning that will give you background to innovate in your environment

  • Who This Book Is For

    If you are a data scientist who performs machine learning on a regular basis, are familiar with deep neural networks, and now want to gain expertise in working with convoluted neural networks, then this book is for you. Some familiarity with C++ or Python is assumed.

    What You Will Learn

  • Set up your computing environment and install TensorFlow

  • Build simple TensorFlow graphs for everyday computations

  • Apply logistic regression for classification with TensorFlow

  • Design and train a multilayer neural network with TensorFlow

  • Intuitively understand convolutional neural networks for image recognition

  • Bootstrap a neural network from simple to more accurate models

  • See how to use TensorFlow with other types of networks

  • Program networks with SciKit-Flow, a high-level interface to TensorFlow

  • In Detail

    Dan Van Boxel’s Deep Learning with TensorFlow is based on Dan’s best-selling TensorFlow video course. With deep learning going mainstream, making sense of data and getting accurate results using deep networks is possible. Dan Van Boxel will be your guide to exploring the possibilities with deep learning; he will enable you to understand data like never before. With the efficiency and simplicity of TensorFlow, you will be able to process your data and gain insights that will change how you look at data.

    With Dan’s guidance, you will dig deeper into the hidden layers of abstraction using raw data. Dan then shows you various complex algorithms for deep learning and various examples that use these deep neural networks. You will also learn how to train your machine to craft new features to make sense of deeper layers of data.

    In this book, Dan shares his knowledge across topics such as logistic regression, convolutional neural networks, recurrent neural networks, training deep networks, and high level interfaces. With the help of novel practical examples, you will become an ace at advanced multilayer networks, image recognition, and beyond.

    Style and Approach

    This book is your go-to guide to becoming a deep learning expert in your organization. Dan helps you evaluate common and not-so-common deep neural networks with the help of insightful examples that you can relate to, and show how they can be exploited in the real world with complex raw data.

    Table of contents

    1. Hands-On Deep Learning with TensorFlow
      1. Table of Contents
      2. Hands-On Deep Learning with TensorFlow
      3. Credits
      4. About the Author
      5. www.PacktPub.com
        1. eBooks, discount offers, and more
        2. Why subscribe?
      6. Customer Feedback
      7. Preface
        1. What this book covers
        2. What you need for this book
        3. Who this book is for
        4. Conventions
        5. Reader feedback
        6. Customer support
        7. Downloading the example code
        8. Downloading the color images of this book
        9. Errata
        10. Piracy
        11. Questions
      8. 1. Getting Started
        1. Installing TensorFlow
          1. TensorFlow – main page
          2. TensorFlow – the installation page
          3. Installing via pip
          4. Installing via CoCalc
        2. Simple computations
          1. Defining scalars and tensors
          2. Computations on tensors
          3. Doing computation
          4. Variable tensors
          5. Viewing and substituting intermediate values
        3. Logistic regression model building
          1. Introducing the font classification dataset
          2. Logistic regression
          3. Getting data ready
          4. Building a TensorFlow model
        4. Logistic regression training
          1. Developing the loss function
          2. Training the model
          3. Evaluating the model accuracy
          4. Summary
      9. 2. Deep Neural Networks
        1. Basic neural networks
          1. Log function
          2. Sigmoid function
        2. Single hidden layer model
          1. Exploring the single hidden layer model
          2. Backpropagation
        3. Single hidden layer explained
          1. Understanding weights of the model
        4. The multiple hidden layer model
          1. Exploring the multiple hidden layer model
        5. Results of the multiple hidden layer
          1. Understanding the multiple hidden layers graph
        6. Summary
      10. 3. Convolutional Neural Networks
        1. Convolutional layer motivation
          1. Multiple features extracted
        2. Convolutional layer application
          1. Exploring the convolution layer
        3. Pooling layer motivation
          1. Max pooling layers
        4. Pooling layer application
        5. Deep CNN
          1. Adding convolutional and pooling layer combo
          2. CNN to classify our fonts
        6. Deeper CNN
          1. Adding a layer to another layer of CNN
        7. Wrapping up deep CNN
        8. Summary
      11. 4. Introducing Recurrent Neural Networks
        1. Exploring RNNs
          1. Modeling the weights
          2. Understanding RNNs
        2. TensorFlow learn
          1. Setup
          2. Logistic regression
        3. DNNs
          1. Convolutional Neural Networks (CNNs) in Learn
          2. Extracting weights
        4. Summary
      12. 5. Wrapping Up
        1. Research evaluation
        2. A quick review of all the models
          1. The logistic regression model
          2. The single hidden layer neural network model
          3. Deep neural network
          4. Convolutional neural network
          5. Deep convolutional neural network
        3. The future of TensorFlow
          1. Some more TensorFlow projects
        4. Summary
      13. Index

    Product information

    • Title: Hands-On Deep Learning with TensorFlow
    • Author(s): Dan Van Boxel
    • Release date: July 2017
    • Publisher(s): Packt Publishing
    • ISBN: 9781787282773