Machine and Deep Learning Using MATLAB

1 Unsupervised Machine Learning (ML) Techniques

Introduction

As quoted by MATLAB R2021b built-in help, machine learning (ML) teaches computers to do what comes naturally to humans: Learn from experience. Machine learning algorithms utilize computational methods to directly learn (or extract) information from data without relying on a deterministic model. The set of algorithms adaptively improve their performance as the number of samples available for learning increases. ML uses two types of learning techniques: Unsupervised and supervised.

The unsupervised ML techniques can be used to weigh the importance of predictor variables relative to each other, without the influence of the response variable. Remember, birds of feather (feature) flock (cluster) together. Unsupervised learning finds hidden patterns or intrinsic structures in data. It is used to draw inferences from datasets consisting of input data without labeled responses. Clustering is the most common unsupervised learning technique. It is used for exploratory data analysis to find hidden patterns or groupings in data. For example, applications where clustering can be used include gene sequence analysis, market research, and object recognition.

Supervised ML, which trains a model on known input (predictor) and output (response) data so that it can predict future outputs. The aim of supervised machine learning is to build a model that makes predictions based on evidence in the presence of uncertainty. A supervised learning ...