Machine Learning

Abstract

Machine learning is an application of Artificial Intelligence. While AI is the umbrella term
given for machines emulating human abilities, machine learning is a specific branch of AI
where machines are trained to learn how to process and make use of data. The objective of machine learning is not only for effective data collection, but also to make use of the ever-increasing amounts being gathered by manipulating and analyzing them without
heavy human input. Machine learning can be defined as a method of mathematical analysis, often using well-known and familiar methods, with a different focus than the traditional analytical practice in applied subjects. The key idea is that flexible, automated methods are used to find patterns within data, with a primary focus on making predictions for future data. There are several real-time applications of machine learning such as Image Recognition, Biometric Recognition, Speech Recognition, Handwriting Recognition, Medical Diagnosis, Traffic prediction, Text Retrieval, Product recommendations, Self-driving cars, Virtual Personal Assistant, Online Fraud Detection, Natural Language Processing, and so on. Machine Learning paradigms are defined in three types, namely Supervised Learning, Unsupervised Learning, and Reinforcement Learning. Supervised learning algorithms are designed to learn by example. It is called supervised learning because the process of an algorithm learning from the training dataset can be thought of as a teacher supervising the learning process. Unsupervised learning deals with unlabelled data means here we have input data and no corresponding output variable. This is further classified into Clustering and Association. In Reinforcement Learning, the machine or agent atomically learns using feedback without any labeled data. Here the agent learns itself from its experience. In this book, the student will find the theoretical concepts and the practical knowledge needed to quickly and efficiently apply these strategies to challenging machine learning problems. The students learn how to understand a problem, be able to represent data, select and correct skills, interpret results correctly, and practice effective analysis of outcomes to make strategic decisions.