| The Machine Learning Toolbox: For Non-Mathematicians Contributor(s): Letort, Brian (Author) |
|
 |
ISBN: 1794302689 ISBN-13: 9781794302686 Publisher: Independently Published OUR PRICE: $19.00 Product Type: Paperback Published: January 2019 |
| Additional Information |
| BISAC Categories: - Computers | Neural Networks |
| Physical Information: 0.39" H x 5" W x 8" (0.41 lbs) 182 pages |
| Descriptions, Reviews, Etc. |
| Publisher Description: The Machine Learning Toolbox provides the theory and foundation for Machine Learning in a business setting. Given the Data Science field is rapidly evolving, attempting to maintain knowledge of this movement can become overwhelming. This book focuses on the foundational aspects of Machine Learning across the basic and proven algorithms. Additionally, this book asserts that the common and simple algorithms can solve the majority of business problems. If you are a seasoned Data Scientist, this book will only reinforce what you already know. If you are looking to enter the field of data science, this book is for you. If you are a software engineer looking to apply data science within your software, this book is for you. If you are in management and looking to extract new patterns from existing data, this book is for you. If you are just interested in the hype surrounding data science, this book is for you. Finally, if you are an executive who is attempting to assemble an organizational analytics strategy, this book is for you. This book focuses on the benefits, drawbacks, constraints, and assumptions of the common algorithms. Doing so enables the quick application and ability to determine the proper algorithm use. While this book does not include code from Python, R, Java, or some other language, it does focus on the foundations that can be applied to any tool or language. Upon reading this book, you will be armed with a common toolbox of machine learning algorithms. What makes this book different is my attempt to reduce the complications of the inherent mathematics and statistics. While both are critical to the use of the discussed algorithms, I believe there is an approach that can explain the algorithms without the underlying complexity. |