Book Image

Statistics for Machine Learning

By : Pratap Dangeti
Book Image

Statistics for Machine Learning

By: Pratap Dangeti

Overview of this book

Complex statistics in machine learning worry a lot of developers. Knowing statistics helps you build strong machine learning models that are optimized for a given problem statement. This book will teach you all it takes to perform the complex statistical computations that are required for machine learning. You will gain information on the statistics behind supervised learning, unsupervised learning, reinforcement learning, and more. You will see real-world examples that discuss the statistical side of machine learning and familiarize yourself with it. You will come across programs for performing tasks such as modeling, parameter fitting, regression, classification, density collection, working with vectors, matrices, and more. By the end of the book, you will have mastered the statistics required for machine learning and will be able to apply your new skills to any sort of industry problem.
Table of Contents (16 chapters)
Title Page
Credits
About the Author
About the Reviewer
www.PacktPub.com
Customer Feedback
Preface

Dropout in neural networks


Dropout is regularization in neural networks to avoid overfitting of the data. Typically, dropout is 0.2 (80 percentage of neurons present randomly all the time) in initial layers and 0.5 in middle layers. One intuitive way to understand the dropout concept would be with the office team, in which a few team members are good with communication with clients though they are not good with technical details, whereas a few are good with technical knowledge but do not have good enough communication skills. Let's say some of the members take leave from the office, and then other members try to fill the shoes of others for the completion of work. In this way, team members who are good with communication will also learn technical details similarly; a few other team members who are good with technical knowledge also learn communication with clients. In this way, all team members will become independent and robust enough to perform all types of work, which is good for the...