Cover image for Automated Machine Learning with AutoKeras

Automated Machine Learning with AutoKeras

Release Date: 2021/05/01
ISBN: 9781800567641
Topic:
0%
17
Chapters
0-1
Hours read
0k
Total Words
    Start Reading Now    
       Add to Wishlist       
View table of contents

Create better and easy-to-use deep learning models with AutoKeras

Key Features

  • Design and implement your own custom machine learning models using the features of AutoKeras
  • Learn how to use AutoKeras for techniques such as classification, regression, and sentiment analysis
  • Get familiar with advanced concepts as multi-modal, multi-task, and search space customization

Book Description

AutoKeras is an AutoML open-source software library that provides easy access to deep learning models. If you are looking to build deep learning model architectures and perform parameter tuning automatically using AutoKeras, then this book is for you.

This book teaches you how to develop and use state-of-the-art AI algorithms in your projects. It begins with a high-level introduction to automated machine learning, explaining all the concepts required to get started with this machine learning approach. You will then learn how to use AutoKeras for image and text classification and regression. As you make progress, you'll discover how to use AutoKeras to perform sentiment analysis on documents. This book will also show you how to implement a custom model for topic classification with AutoKeras. Toward the end, you will explore advanced concepts of AutoKeras such as working with multi-modal data and multi-task, customizing the model with AutoModel, and visualizing experiment results using AutoKeras Extensions.

By the end of this machine learning book, you will be able to confidently use AutoKeras to design your own custom machine learning models in your company.

What you will learn

  • Set up a deep learning workstation with TensorFlow and AutoKeras
  • Automate a machine learning pipeline with AutoKeras
  • Create and implement image and text classifiers and regressors using AutoKeras
  • Use AutoKeras to perform sentiment analysis of a text, classifying it as negative or positive
  • Leverage AutoKeras to classify documents by topics
  • Make the most of AutoKeras by using its most powerful extensions

Who this book is for

This book is for machine learning and deep learning enthusiasts who want to apply automated ML techniques to their projects. Prior basic knowledge of Python programming and machine learning is expected to get the most out of this book.

Table of Contents

  1. Automated Machine Learning with AutoKeras
  2. Contributors
  3. About the author
  4. About the reviewers
  5. Preface
    1. Who this book is for
    2. What this book covers
    3. To get the most out of this book
    4. Download the example code files
    5. Download the color images
    6. Conventions used
    7. Get in touch
    8. Reviews
  6. Section 1: AutoML Fundamentals
  7. Chapter 1: Introduction to Automated Machine Learning
    1. The anatomy of a standard ML workflow
    2. Data ingestion
    3. Data preprocessing
    4. Model deployment
    5. Model monitoring
    6. What is AutoML?
    7. Differences from the standard approach
    8. Types of AutoML
    9. Automated feature engineering
    10. Automated model choosing and hyperparameter optimization
    11. Automated neural network architecture selection
    12. Summary
    13. Further reading
  8. Chapter 2: Getting Started with AutoKeras
    1. Technical requirements
    2. What is deep learning?
    3. What is a neural network and how does it learn?
    4. How do deep learning models learn?
    5. Why AutoKeras?
    6. How to run the AutoKeras experiments?
    7. Installing AutoKeras
    8. Installing AutoKeras in the cloud
    9. Installing AutoKeras locally
    10. Hello MNIST: Implementing our first AutoKeras experiment
    11. Importing the needed packages
    12. Getting the MNIST dataset
    13. How are the digits distributed?
    14. Creating an image classifier
    15. Evaluating the model with the test set
    16. Visualizing the model
    17. Creating an image regressor
    18. Evaluating the model with the test set
    19. Visualizing the model
    20. Summary
  9. Chapter 3: Automating the Machine Learning Pipeline with AutoKeras
    1. Understanding tensors
    2. What is a tensor?
    3. Types of tensors
    4. Preparing the data to feed deep learning models
    5. Data preprocessing operations for neural network models
    6. Loading data into AutoKeras in multiple formats
    7. Splitting your dataset for training and evaluation
    8. Why you should split your dataset
    9. How to split your dataset
    10. Summary
  10. Section 2: AutoKeras in Practice
  11. Chapter 4: Image Classification and Regression Using AutoKeras
    1. Technical requirements
    2. Surpassing classical neural networks
    3. Creating a CIFAR-10 image classifier
    4. Creating and fine-tuning a powerful image classifier
    5. Improving the model performance
    6. Evaluating the model with the test set
    7. Visualizing the model
    8. Creating an image regressor to find out the age of people
    9. Creating and fine-tuning a powerful image regressor
    10. Improving the model performance
    11. Evaluating the model with the test set
    12. Visualizing the model
    13. Summary
  12. Chapter 5: Text Classification and Regression Using AutoKeras
    1. Technical requirements
    2. Working with text data
    3. Tokenization
    4. Vectorization
    5. Understanding RNNs
    6. One-dimensional CNNs (Conv1D)
    7. Creating an email spam detector
    8. Creating the spam predictor
    9. Evaluating the model
    10. Visualizing the model
    11. Predicting news popularity in social media
    12. Creating a text regressor
    13. Evaluating the model
    14. Visualizing the model
    15. Improving the model performance
    16. Evaluating the model with the test set
    17. Summary
  13. Chapter 6: Working with Structured Data Using AutoKeras
    1. Technical requirements
    2. Understanding structured data
    3. Working with structured data
    4. Creating a structured data classifier to predict Titanic survivors
    5. Creating the classifier
    6. Evaluating the model
    7. Visualizing the model
    8. Creating a structured data regressor to predict Boston house prices
    9. Creating a structure data regressor
    10. Evaluating the model
    11. Visualizing the model
    12. Summary
  14. Chapter 7: Sentiment Analysis Using AutoKeras
    1. Technical requirements
    2. Creating a sentiment analyzer
    3. Creating the sentiment predictor
    4. Evaluating the model
    5. Visualizing the model
    6. Analyzing the sentiment in specific sentences
    7. Summary
  15. Chapter 8: Topic Classification Using AutoKeras
    1. Technical requirements
    2. Understanding topic classification
    3. Creating a news topic classifier
    4. Creating the classifier
    5. Evaluating the model
    6. Visualizing the model
    7. Evaluating the model
    8. Customizing the model search space
    9. Summary
  16. Section 3: Advanced AutoKeras
  17. Chapter 9: Working with Multimodal and Multitasking Data
    1. Technical requirements
    2. Exploring models with multiple inputs or outputs
    3. What is AutoModel?
    4. What is multimodal?
    5. What is multitask?
    6. Creating a multitask/multimodal model
    7. Creating the model
    8. Visualizing the model
    9. Customizing the search space
    10. Summary
  18. Chapter 10: Exporting and Visualizing the Models
    1. Technical requirements
    2. Exporting your models
    3. How to save and load a model
    4. Visualizing your models with TensorBoard
    5. Using callbacks to log the model state
    6. Setting up and loading TensorBoard
    7. Sharing your ML experiment results with TensorBoard.dev
    8. Visualizing and comparing your models with ClearML
    9. Adding ClearML to code
    10. Comparing experiments
    11. Summary
    12. A final few words
    13. Why subscribe?
  19. Other Books You May Enjoy
    1. Packt is searching for authors like you
    2. Leave a review - let other readers know what you think
3.129.247.196