Externally indexed torrent

If you are the original uploader, contact staff to have it moved to your account

Textbook in PDF format

A step-by-step guide to get started with Machine Learning.
Key Features
- Understand different types of Machine Learning like Supervised, Unsupervised, Semi-supervised, and Reinforcement learning.
- Learn how to implement Machine Learning algorithms effectively and efficiently.
- Get familiar with the various libraries &amp tools for Machine Learning.
Description
Should I choose supervised learning or reinforcement learning? Which algorithm is best suited for my application? How does Deep Learning advance the capacities of problem-solving? If you have found yourself asking these questions, this book is specially developed for you.
The book will help readers understand the core concepts of Machine Learning and techniques to evaluate any Machine Learning model with ease. The book starts with the importance of Machine Learning by analyzing its impact on the global landscape. The book also covers Supervised and Unsupervised ML along with Reinforcement Learning. In subsequent chapters, the book explores these topics in even greater depth, evaluating the pros and cons of each and exploring important topics such as Bias-Variance Tradeoff, Clustering, and Dimensionality Reduction. The book also explains model evaluation techniques such as Cross-Validation and GridSearchCV. The book also features mind maps which help enhance the learning process by making it easier to learn and retain information.
The readers will be exposed to the depth of learning which is summarized as follows:
In Chapter 1, we introduce the idea of Machine Learning and the various reasons it has gained popularity globally. We then discuss what the different tools and software required for successfully implementing Machine Learning models are. We give a brief description of the types of Machine Learning like Supervised, Unsupervised, Semi-supervised, and Reinforcement learning. At the end of the chapter, we see what the different challenges one can encounter are during their implementation.
In Chapter 2, we discuss some of the important terms related to Machine Learning like Generalization, Overfitting, and Underfitting. We then move on to explain the Bias-Variance Tradeoff. We take a detailed look at each of the supervised machine learning algorithms and the different scenarios where they can be used. We also explain how to implement these algorithms successfully and what are the pros and cons of each.
In Chapter 3, we introduce some of the basic concepts of unsupervised machine learning. We look at two of the broad categories of unsupervised machine learning namely Clustering and Dimensionality Reduction. We explain each of these categories in detail. We see the different types of algorithms present in each category, explain their working, and list the pros and cons for the same.
In Chapter 4, we cover some of the most important and frequently used evaluation techniques. We start by explaining Cross-Validation and its different types. We then move on to a complex technique known as GridSearchCV. These are advanced techniques utilized to see the performance of the model. We then introduce evaluation metrics for classification as well as regression. Each one of these evaluation metrics has its pros and cons. The types of metrics to be chosen depends upon the problem at hand.
In Chapter 5, we explain Reinforcement Learning and the concepts behind its implementation. For the sake of this book, we have tried to keep things simple and explain everything at a basic level. We discuss some important terms associated with reinforcement learning like Policy, Policy gradients, Markov Decision Processes. We then look at some of the mathematics behind the successful implementation of reinforcement learning. Towards the end of the chapter, we explain some types of reinforcement learning. In this book, we have only covered the basic and necessary information of these advanced algorithms.
In Chapter 6, we look at some advanced techniques and technologies. We start off by learning about TensorFlow which is the library used for implementing neural networks. We then move onto explaining the different types of neural networks. We explain in detail the fundamentals behind the Artificial Neural Network and its working. We then discuss Convolutional Neural Networks and their architecture. At last, we explain the basic implementation and working of Recurrent Neural Networks and their use case scenarios.
In the Appendix, we provide the practice questions segregated according to the topics covered in chapters 1 to 6. We have observed that learners often practice questions after studying multiple topics. Hence, around 350 practice questions, including short answer type, long answer type, multiple choice, true-false, and fill-in-the-blank type questions, are shared in this section. Many questions have the answers written next to them for your help. Readers can read multiple chapters without breaking the flow as the contents are written using simple English words. Practice questions are presented in the Appendix to revise and refine their understanding.
This book is a one-stop solution for covering basic ML concepts in detail and the perfect stepping stone to becoming an expert in ML and Deep Learning and even applying them to different professions.
What you will learn
- Understand important concepts to fully grasp the idea of supervised learning.
- Get familiar with the basics of unsupervised learning and some of its algorithms.
- Learn how to analyze the performance of your Machine Learning models.
- Explore the different methodologies of Reinforcement Learning.
- Learn how to implement different types of Neural networks.
Who this book is for
This book is aimed at those who are new to Machine Learning and Deep Learning or want to extend their ML knowledge. Anyone looking to apply ML to data in their profession will benefit greatly from this book.
1. Introduction to Machine Learning
2. Supervised Learning
3. Unsupervised Learning
4. Model Evaluation
5. Reinforcement Learning
6. Neural Networking and Deep Learning
7. Appendix: Machine Learning Questions