Unsupervised Learning
The book till now has focused on supervised learning and the models that learn via supervised learning. Starting from this chapter we will explore a less explored and more challenging area of unsupervised learning, self-supervised learning, and contrastive learning. In this chapter, we will delve deeper into some popular and useful unsupervised learning models. In contrast to supervised learning, where the training dataset consists of both the input and the desired labels, unsupervised learning deals with a case where the model is provided with only the input. The model learns the inherent input distribution by itself without any desired label guiding it. Clustering and dimensionality reduction are the two most commonly used unsupervised learning techniques. In this chapter, we will learn about different machine learning and neural network techniques for both. We will cover techniques required for clustering and dimensionality reduction, and go into the detail...
