This book will teach you machine learning in a project-based way, touching on a broad range of topics from the basics to the latest deep learning techniques. In addition, it covers often overlooked topics, from productionizing machine learning models to collecting datasets. It’s focused on the practical, so it’s ideal for software engineers looking to deep dive into machine learning.
By the end of the book, you will have implemented a wide variety of projects that will serve as a great portfolio. The knowledge from the book together with the portfolio will help you launch a career in machine learning, as a data scientist or a machine learning engineer.
The main language of the book is Python, and we will use the standard PyData stack: NumPy, SciPy, Pandas, and Scikit-Learn. In addition, we will learn how to use other libraries, like Keras with TensorFlow for deep learning. Finally, we will cover infrastructure and deployment technologies like Flask, Docker, and AWS.
Three chapters available now, and after reading them, you will understand the problems that machine learning can solve and will have finished two projects: predicting the price of a car and determining whether a customer is going to churn.
As additional chapters become available, you will also learn how to evaluate machine learning models, how to make them available as a web service, and much more!