AutoML tools are the need of the hour for data scientists to reduce their workloads in the world where the generation of data is only increasing exponentially. Readily available AutoML tools make the data science practitioner’s work more comfortable and covers necessary foundations needed to create automated machine learning modules. And with the spur in data and the potential that this data holds, data scientists will benefit more by using AutoML capabilities. As we approach the midpoint of 2020, it is slowly being recognised that this year will see an increase in adaptation of AutoML.
With the massive potential of AutoML about to burst, non-data science professionals and data science practitioners will look to get a more comprehensive view on the technology. Below are some books that will help gain a better understanding of AutoML’s features, applications, and what the technology is about:
Automated Machine Learning: Methods, Systems, Challenges
This book gives a comprehensive tutorial level overview of the methods underlying AutoML by giving the readers a complete understanding of the key concepts. There are in-depth descriptions of AutoML systems and implementation in the context of actual systems. Not only does this entail different kinds of AutoML approaches, but it also gives pros and cons about the approach.
Some topics included in this book are hyperparameter optimisation, meta-learning, neural architecture search, Auto-WEKA: Automatic Model Selection and Hyperparameter Optimisation in WEKA etc.
AutoML Models A Complete Guide – 2019 Edition
This book helps one get a clear picture of AutoML and ask the right questions, which will make the AutoML model investments better. AutoML Models A Complete Guide contains the majority of the tools one needs for an in-depth AutoML Model Self Assessment. The book features 900 case-based questions organised into seven core areas of process design, which will give one an idea about where the AutoML models need improvement.
These questions will make one diagnose AutoML Models projects, initiatives, organisations and businesses better and implement evidence-based best practice strategies aligned with overall goals. One also learns to better integrate recent advances in AutoML Models and process design strategies into practice in accordance with best practice guidelines.
Hands-On Automated Machine Learning
This 282-page book is solely aimed at teaching how to automate different tasks in the machine learning pipeline. Authored by Sibanjan Das, Umit Merk Cakmak, Hands-On Automated Machine Learning gives a detailed description on how to work on machine learning pipelines like data processing, feature selection, model optimisation, model training and many more. It also demonstrates how one can use the existing automated libraries, like auto-sklearn and MLBox, and create and extend custom AutoML components for machine learning.
The book features building automated models for different machine learning components, understanding each of these components and learn to use different open-source AutoML and feature engineering platforms.
Hands-On Artificial Intelligence on Google Cloud Platform
This book is written by Anand Deshpande, Manish Kumar and Vikram Chaudhari. In this book, one will be able to understand the basics of cloud computing and explore GCP along with learning to implement machine learning algorithms with Google Cloud AutoML.
This book basically acts as a guide and shows how GCP tools can be used to build AI-powered applications with ease and to manage thousands of AI-powered implementations on the cloud. One will also be able to learn how to implement Cloud AutoML to demonstrate the use of streaming components to perform data analytics and understand how DialogFlow can be used to create a conversational interface. With other activities, in the end, one will be able to build and deploy AI applications to production with the help of a use case.
Practical Automated Machine Learning On Azure.
This book was authored by Deepak Mukunthu, Parashar Shah, Wee Hyong Tok. This provides a mix of technical depth, hands-on examples and includes case studies that show how customers are leveraging AutoML capabilities to solve real-world problems.
The book covers how different industries use AutoML, tutorial with AutoML using Azure, exploring algorithm selection, auto featurisation, and hyperparameter tuning, understand how different professions can use and benefit from AutoML with the tool they are already familiar with and finally, how to get started on AutoML for use cases including regression, forecasting and classification.