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.
Author(s): Luis Sobrecueva
Edition: 1
Publisher: Packt Publishing
Year: 2021
Language: English
Commentary: Vector PDF
Pages: 194
City: Birmingham, UK
Tags: Machine Learning; Deep Learning; Regression; Convolutional Neural Networks; Recurrent Neural Networks; Classification; Sentiment Analysis; Pipelines; Text Classification; Automation; AutoKeras
Cover
Title Page
Copyright and Credits
Contributors
Table of Contents
Preface
Section 1: AutoML fundamentals
Chapter 1: Introduction to Automated Machine Learning
The anatomy of a standard ML workflow
Data ingestion
Data preprocessing
Model deployment
Model monitoring
What is AutoML?
Differences from the standard approach
Types of AutoML
Automated feature engineering
Automated model choosing and hyperparameter optimization
Automated neural network architecture selection
Summary
Further reading
Chapter 2: Getting Started with AutoKeras
Technical requirements
What is deep learning?
What is a neural network and how does it learn?
How do deep learning models learn?
Why AutoKeras?
How to run the AutoKeras experiments?
Installing AutoKeras
Installing AutoKeras in the cloud
Installing AutoKeras locally
Hello MNIST: Implementing our first AutoKeras experiment
Importing the needed packages
Getting the MNIST dataset
How are the digits distributed?
Creating an image classifier
Evaluating the model with the test set
Visualizing the model
Creating an image regressor
Evaluating the model with the test set
Visualizing the model
Summary
Chapter 3: Automating the Machine Learning Pipeline with AutoKeras
Understanding tensors
What is a tensor?
Types of tensors
Preparing the data to feed deep learning models
Data preprocessing operations for neural network models
Loading data into AutoKeras in multiple formats
Splitting your dataset for training and evaluation
Why you should split your dataset
How to split your dataset
Summary
Section 2: AutoKeras in practice
Chapter 4: Image Classification and Regression Using AutoKeras
Technical requirements
Surpassing classical neural networks
Creating a CIFAR-10 image classifier
Creating and fine-tuning a powerful image classifier
Improving the model performance
Evaluating the model with the test set
Visualizing the model
Creating an image regressor to find out the age of people
Creating and fine-tuning a powerful image regressor
Improving the model performance
Evaluating the model with the test set
Visualizing the model
Summary
Chapter 5: Text Classification and Regression Using AutoKeras
Technical requirements
Working with text data
Tokenization
Vectorization
Understanding RNNs
One-dimensional CNNs (Conv1D)
Creating an email spam detector
Creating the spam predictor
Evaluating the model
Visualizing the model
Predicting news popularity in social media
Creating a text regressor
Evaluating the model
Visualizing the model
Improving the model performance
Evaluating the model with the test set
Summary
Chapter 6: Working with Structured Data Using AutoKeras
Technical requirements
Understanding structured data
Working with structured data
Creating a structured data classifier to predict Titanic survivors
Creating the classifier
Evaluating the model
Visualizing the model
Creating a structured data regressor to predict Boston house prices
Creating a structure data regressor
Evaluating the model
Visualizing the model
Summary
Chapter 7: Sentiment Analysis Using AutoKeras
Technical requirements
Creating a sentiment analyzer
Creating the sentiment predictor
Evaluating the model
Visualizing the model
Analyzing the sentiment in specific sentences
Summary
Chapter 8: Topic Classification Using AutoKeras
Technical requirements
Understanding topic classification
Creating a news topic classifier
Creating the classifier
Evaluating the model
Visualizing the model
Evaluating the model
Customizing the model search space
Summary
Section 3: Advanced AutoKeras
Chapter 9: Working with Multimodal and Multitasking Data
Technical requirements
Exploring models with multiple inputs or outputs
What is AutoModel?
What is multimodal?
What is multitask?
Creating a multitask/multimodal model
Creating the model
Visualizing the model
Customizing the search space
Summary
Chapter 10: Exporting and Visualizing the Models
Technical requirements
Exporting your models
How to save and load a model
Visualizing your models with TensorBoard
Using callbacks to log the model state
Setting up and loading TensorBoard
Sharing your ML experiment results with TensorBoard.dev
Visualizing and comparing your models with ClearML
Adding ClearML to code
Comparing experiments
Summary
A final few words
Why subscribe?
About Packt
Other Books You May Enjoy
Index
