Machine Learning (ML) belongs to a category of algorithms that allows for more accurate prediction without being explicitly programmed. It is similar to data mining and predictive modeling, especially where all three techniques require searching for patterns and adjusting program actions. Machine Learning algorithms are classified into supervised and unsupervised learning algorithms. In the case of supervised learning algo-rithms, data scientists have a set of training data through which they build the model. The model is tested with testing data. In unsupervised learning algorithms, the model is built by not using the training dataset but by discovering new patterns. This book is for neophyte users who are getting acquainted to the concept of Machine Learning.
It is a myth that math is the primary prerequisite for Machine Learning. However, data analysis is the first skill requirement to work with Machine Learning. This is particularly true for beginners. Most of the work on using Machine Learning algorithms is centered on data preparation. After a compendious introduction on Machine Learning, the mathematics required for working with Machine Learning algorithms is dealt with in this book. This is followed in depth by the concept of data preprocessing. This helps the user understand the mathematics behind data preparation.
This book is written keeping in mind the academic needs and requirements of undergraduate students. The language used in the book is simple and there are more than adequate examples. This book is an effort to deliver to the best of our abilities the concept of Machine Learning to beginners. It was a real challenge that was worth it at the end. Our first-time writing experience has been a wonderful journey, from the time we decided to write the book till its present form. It has really been a challenging experience to complete the latest updates about the subject, keeping in mind that we are catering to first-time readers.
This book offers the readers the basics of Machine Learning in a very simple, user-friendly language. While browsing the Table of Contents, you will realize that you are given an introduction to every concept that comes under the umbrella of Machine Learning.
This book is aimed at students who are new to the topic of machine learning. It is meant for students studying machine learning in their undergraduate and postgraduate courses in information technology. It is also aimed at computer engineering students. It will help familiarize students with the terms and terminologies used in machine learning. We hope that this book serves as an entry point for students to pursue their future studies and careers in machine learning. The worked-out examples in the book are completely focused from academic point of view.
Python is an interactive high-level programming language. It was created by Guido van Rossum during 1985–1990. Its popularity was mainly because it was simple, understandable, easy-to-learn, portable, and interpreted. It is interpreted and interactive because Python can be processed at runtime by the interpreter and interacted directly. Being interpreted, Python does not require separate compilation and execution steps. All this conversion is done internally which makes it easier to run the programs. It supports object-oriented style of programming by encapsulating code within the objects. Python is a very user-friendly language and was designed with the idea of making it accessible to the common man.
The book is organized in four parts. Part I in general introduces the subjects and revision of all the basics required for working with Machine Learning algorithms. There are five chapters in Part I. Chapter 1 gives a brief introduction to Machine Learning. It gives answers to the questions such as: What is machine learning? Where is machine learning used? What are the types of machine learning? Two real-time case studies are also explained in this chapter. Once the reader gets acquainted to the basics of machine learning, Chapter 2 introduces the representation of the model. Chapters 3 and 4 elaborate on the basics of matrices and the basics of Python, which serve as the prerequisite for understanding Machine Learning. Chapter 5 gives an introduction to the different techniques required for data preprocessing.
Part II covers the topic of supervised learning algorithms. Chapter 6 introduces artificial neural networks (ANN). ANN of late has become very popular, with lots of applications using deep learning. So we felt it important that the concept of ANN be introduced to the readers. This is followed in Chapters 7 and 8, which detail regression techniques. Chapter 9 on decision tree, chapter 10 on support vector machine, and chapter 11 on Bayesian classification give extensive examples and solved numericals on supervised learning techniques which are popular and mostly used. Chapter 12 introduces the Hidden Markov Model in brief.
Part III has a chapter on unsupervised learning algorithms, which covers the basics of clustering. The chapter has extensive examples on different types of clustering and expectation maximization. This Part is dedicated only to unsupervised learning techniques.
Part IV has a chapter on optimization techniques. This chapter gives an introduction to formulate optimization problems, and the commonly used derivative-free and derivative-based optimization algorithms.
Навигация
Вход на сайт
Реклама
Machine Learning by Anuradha Srinivasaraghavan 
