This book is aimed at providing a practical guidance and approach for utilizing TensorFlow in the real-world based on Python (a programming language). You are not expected to be an expert in Python or know Python at all. The book is intended for newcomers in the field of Machine Learning (ML) and Artificial Intelligence (AI), especially for those, who do not have any statistical background, but they are really interested to learn the details and approach of building a Machine Learning application. This book is also intended for experienced data scientists, Machine Learning engineers, who are generally too focused on building Machine Learning model(s), investing 60-70% of their time in making the model work with a greater level of accuracy, in some cases, they forget the real application and the use case of the application. In most of these cases they end up what we call "overfitting" of the model. The book is expected to focus on developing a Machine Learning application, and in the process detailing multiple real-world practical challenges, steps of a ML application(s). Honestly speaking, the book is meant for "lazy" engineers, aspiring data scientists, Machine Learning engineers, experienced IT professionals in other fields, who like the authors, hate reading through lengthy books with several hundred pages of mathematical models and equations to even getting started with Machine Learning. Many of us are looking for a book with not more than 100-150 pages to gain an understanding on Machine Learning, and it could be an icing on the cake if the book can do away with minimal to no mathematical equations. There are many books, articles, books, guides and documents published on Artificial Intelligence, Machine Learning, and most of them focus on mathematical equations, building models, they tend to be very lengthy spanning several hundred pages. Of-course, they are aimed at serving an exhaustive content for readers to get a deep understanding on the subjects. The aim of this book is not only to just discuss the Machine Learning models, but also focus on explaining the core of Machine Learning with simple examples on regression, classifications, etc. and then discuss a practical approach and steps to build a productionized Machine Learning models with a practical feature engineering. As you read through the book, hopefully the myths of AI and Machine Learning will be debunked, and you will get a very granular/basic to an implementation level understanding and approach of developing ML applications. At the time of writing and conceptualizing this book (in 2019) the authors ensured to keep the content precise, and limit the length of the book in the range of 100-150 pages for those "lazy" but smart engineers out there. After you read this book you can expect to understand the commonly used terminologies of Machine Learning, Artificial Intelligence, learn a little bit of Python enough to be able to write your own ML code, use TensorFlow to build productionized models.