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
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.
Who is this book 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.
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
The book is a thorough guide about all the aspects of Automated Machine Learning using AutoKeras. Anybody who is currently in ML and wants to dive into AutoML world, AutoKeras library provides all the functionalities, starting from building/tuning sophisticated models and later visualizing those in a single open-source API. Furthermore, AutoKeras helps leveraging computational resources by using GPU. This book is a brilliant resource to understand and deploy AutoML models in all major application areas like image/text classification and regression, sentiment analysis, structured data regression etc.The following features of the book are extremely helpful-Provides hands on experience as all the examples are driven by Jupyter Notebooks with a git-hub link-Examples are often supplemented with ‘to the point’ explanation which aids in understanding technical aspects of the problem.-In the context of data regression, this book provides multitask examples (prediction of multiple output vectors with the same input data) which correlates well with most of the practical regression use cases.-Separate section is included for visualizing and tracking of the deployed models using ClearML (trains)In short, a very useful book for both new and experienced users to understand AutoKeras in a more practical way.
Amazon Verified review
M. PetreyMay 21, 2021
5
As someone who is more familiar with traditional machine learning pipelines but not AutoML, I found this book a great introduction to AutoML and AutoKeras. I appreciated that the code examples were all in Jupyter notebooks, making them very easy to run locally or on Google Colab. Although many of the examples are from data sets folks will be familiar with (MNIST, Titanic, etc.) I appreciated that familiarity when using the new tools - the data sets didn't feel like tropes like they sometimes can. I have less experience with text analytics, and I especially liked the examples with sentiment analysis and topic clustering. The consistent structure across chapters was helpful when approaching the new content. If you're already familiar with automated machine learning, I think you'll still find helpful pieces in this book, either on new topics, visualizing models, or working with more advanced model options.
Amazon Verified review
Dr. Sreenivas BhattiproluJun 24, 2021
5
Machine learning is a rapidly evolving technology that addresses challenges in many fields including, sciences, engineering, business, arts, and humanities. Unfortunately, it is mostly accessible to advanced coders coming from strong computer sciences backgrounds. Machine learning is still not part of the core curriculum for students in these fields. For example, biologists trying to understand sub-cellular features receive training in collecting the best microscope images. But, when it comes to analyzing those images, they tend to spend a significant amount of their valuable research time doing manual tasks that can be easily automated using Machine Learning.Google AI released AutoML to enable coders with limited machine learning skills to automatically train neural networks on their datasets. AutoKeras is an AutoML system based on Keras. It is developed by DATA Lab at Texas A&M University. AutoKeras democratizes machine learning and makes it easy to train neural networks with only a few lines of code in python. In fact, I was amazed by its simplicity when I discovered it in 2020 so I made a couple of training videos for my YouTube channel (@DigitalSreeni).This book provides broader insights into AutoKeras. It summarizes the essence of AutoKeras by walking the reader through a variety of examples including image classification, text classification, and sentiment analysis.I liked the clear explanation of pain points in machine learning workflows and how AutoML addresses these pain points. I particularly liked the comparison of various AutoML tools and why the authors chose to focus on the AutoKeras tool. I appreciate the coverage of AutoKeras installation on Google Colab. Many readers will not have access to GPU for deep learning and Colab makes it freely accessible. The text classification chapter is noteworthy, especially the introduction of common terminology used in tokenization and vectorization. The accompanying exercises in all chapters demonstrate the ability of AutoKeras in simplifying the machine learning process. Finally, I enjoyed the explanation of TensorBoard, a much-needed visualization toolkit to evaluate model performance.My only critical feedback would be about the use of standard data sets such as MNIST and CIFAR-10. Loading custom data is a challenge for novice machine learning engineers, the targeted user base for AutoKeras. It would have been beneficial for the reader to understand the advantage of AutoKeras while working on custom datasets. Also, I believe the book missed an opportunity to make the reader realize the pain of working without AutoKeras. A walk-through exercise without and with AutoKeras would have added icing to the cake.In summary, I recommend this book to new and mid-level machine learning coders. I even advise advanced coders to give it a look as it may help you speed up some of your work. Considering that the book is under 200 pages, it makes an easy read.
Amazon Verified review
Payton SoicherAug 04, 2021
5
I'm a data scientist and I had never heard of AutoKeras before this book. It did a great job explaining what it is, why you would use it, and how to interpret each model that you use. I really enjoyed it
Amazon Verified review
Ignasi FoschMay 21, 2021
4
Those interested in ML and, more specifically, AutoML will probably be already aware of AutoKeras. Luis is an AutoKeras contributor and this book of his is a good dive in into AutoKeras' and the process it helps to implement. It's also interesting to see how this can help people not willing to go into AutoML cloud services build up their own platform.For those who want to get introduced into AutoML, this is a pretty recommendable book. While it requires some prior knowledge on ML, DL, and generic open source projects usage, it's still providing some introduction.
Luis Sobrecueva is a senior software engineer and ML/DL practitioner currently working at Cabify. He has been a contributor to the OpenAI project as well as one of the contributors to the AutoKeras project.
A subscription provides you with full access to view all Packt and licnesed content online, this includes exclusive access to Early Access titles. Depending on the tier chosen you can also earn credits and discounts to use for owning content
How can I cancel my subscription?
To cancel your subscription with us simply go to the account page - found in the top right of the page or at https://subscription.packtpub.com/my-account/subscription - From here you will see the ‘cancel subscription’ button in the grey box with your subscription information in.
What are credits?
Credits can be earned from reading 40 section of any title within the payment cycle - a month starting from the day of subscription payment. You also earn a Credit every month if you subscribe to our annual or 18 month plans. Credits can be used to buy books DRM free, the same way that you would pay for a book. Your credits can be found in the subscription homepage - subscription.packtpub.com - clicking on ‘the my’ library dropdown and selecting ‘credits’.
What happens if an Early Access Course is cancelled?
Projects are rarely cancelled, but sometimes it's unavoidable. If an Early Access course is cancelled or excessively delayed, you can exchange your purchase for another course. For further details, please contact us here.
Where can I send feedback about an Early Access title?
If you have any feedback about the product you're reading, or Early Access in general, then please fill out a contact form here and we'll make sure the feedback gets to the right team.
Can I download the code files for Early Access titles?
We try to ensure that all books in Early Access have code available to use, download, and fork on GitHub. This helps us be more agile in the development of the book, and helps keep the often changing code base of new versions and new technologies as up to date as possible. Unfortunately, however, there will be rare cases when it is not possible for us to have downloadable code samples available until publication.
When we publish the book, the code files will also be available to download from the Packt website.
How accurate is the publication date?
The publication date is as accurate as we can be at any point in the project. Unfortunately, delays can happen. Often those delays are out of our control, such as changes to the technology code base or delays in the tech release. We do our best to give you an accurate estimate of the publication date at any given time, and as more chapters are delivered, the more accurate the delivery date will become.
How will I know when new chapters are ready?
We'll let you know every time there has been an update to a course that you've bought in Early Access. You'll get an email to let you know there has been a new chapter, or a change to a previous chapter. The new chapters are automatically added to your account, so you can also check back there any time you're ready and download or read them online.
I am a Packt subscriber, do I get Early Access?
Yes, all Early Access content is fully available through your subscription. You will need to have a paid for or active trial subscription in order to access all titles.
How is Early Access delivered?
Early Access is currently only available as a PDF or through our online reader. As we make changes or add new chapters, the files in your Packt account will be updated so you can download them again or view them online immediately.
How do I buy Early Access content?
Early Access is a way of us getting our content to you quicker, but the method of buying the Early Access course is still the same. Just find the course you want to buy, go through the check-out steps, and you’ll get a confirmation email from us with information and a link to the relevant Early Access courses.
What is Early Access?
Keeping up to date with the latest technology is difficult; new versions, new frameworks, new techniques. This feature gives you a head-start to our content, as it's being created. With Early Access you'll receive each chapter as it's written, and get regular updates throughout the product's development, as well as the final course as soon as it's ready.We created Early Access as a means of giving you the information you need, as soon as it's available. As we go through the process of developing a course, 99% of it can be ready but we can't publish until that last 1% falls in to place. Early Access helps to unlock the potential of our content early, to help you start your learning when you need it most. You not only get access to every chapter as it's delivered, edited, and updated, but you'll also get the finalized, DRM-free product to download in any format you want when it's published. As a member of Packt, you'll also be eligible for our exclusive offers, including a free course every day, and discounts on new and popular titles.