Machine Learning: The Complete Beginner’s Guide to Learn and Effectively Understand Machine Learning Techniques

by Antonio Robert

Machine learning is one of the principal areas of artificial intelligence.

It concerns the study and the development of quantitative models allowing a computer to accomplish tasks without it being explicitly programmed to do them. Learning in this context means recognizing complex shapes and making smart decisions. Given all the existing entries, the complexity of doing so lies in the fact that the set of possible decisions is usually very difficult to enumerate. The machine learning algorithms have, therefore, been designed to gain knowledge about the problem to be addressed based on a set of limited data from this problem.

This guidebook is going to take some time to explore machine learning, and what it is all about. There are so many different aspects of machine learning and how to make it work for your needs, and all of it is found in this guidebook. Some of the different topics that you will be able to learn about inside include:
Get access to free software and data sets so you can try out your very own machine learning software. See how advanced machine learning will impact our world in the future!

Also, this book presents the scientific foundations of the theory of supervised learning, the most widespread algorithms developed in this field as well as the two frameworks of semi-supervised learning and scheduling, at a level accessible to master's students and engineering students. We had here the concern to provide a coherent presentation linking the theory to the algorithms developed in this sphere. But this study is not limited to present these foundations; you will find some programs of classical algorithms proposed in this manuscript, written in C language (language both simple and popular), and for readers who want to know how it works. These models are sometimes referred to as black boxes.

Who is this book directed to:  

The engineering students, master’s students, including doctoral students in applied mathematics, algorithmic, operations research, production management, decision support.

Also, to engineers, teacher-researchers, computer scientists, industrialists, economists, and decision-makers who have to resolve problems of classification, partitioning, and scheduling on a large scale.

In this book, you will attain helpful information for getting started, such as:

Why Use Neural Networks?
The Different Types Of Learning
Machine Learning In Practice    
Reinforcement Learning 
Learning by reinforcement         
Neural Networks   
Tasks Of Neural Networks
Neural Networks versus Conventional Computers  

122 pages, Kindle Edition

Published July 1, 2019

Reviews

[Lilian Martins · Rating 3 out of 5]

Bem básico, traz os conceitos principais para iniciantes.