A Taxonomy of Machine Learning Techniques

Abstract

Learning is any process by which a system improves performance from experience. Training a model simply means learning (i.e., determining) good values for all the weights and therefore the bias from labeled examples. Machine learning (ML) is a sub-field of artificial intelligence that creates machines which exhibits learning capability and improve their performance from experience without being explicitly programmed. ML focuses on the creation of computer programs that can access data and use it to learn from themselves. In other words, it is the study of algorithms that improve their performance (P) at some task (T) with some experience (E). Now, as we know about learning and machine learning let’s see why the machine learning is needed — it is needed because it provides smart alternatives to analyzing huge volume of data (i.e., Big data). Due to the rapid development of efficient algorithms and data-driven models for real-time processing of datasets, ML can assists to handle the classification and categorical problems. A taxonomy of popular machine learning techniques are, such as supervised learning, unsupervised learning, semi supervised learning, reinforcement learning, etc. In addition to that, the state-of-art applications of machine learning are — image recognition, speech recognition, product recommendations, self-driving cars, space exploration, online fraud detection, Robotics, healthcare, etc. The paper will outline the taxonomy of popular machine learning techniques.