What Every Engineer Should Know About Data-Driven Analytics

5 Unsupervised Learning

DOI: 10.1201/9781003278177-5

Unsupervised learning involves discovering the hidden patterns or structures from a dataset without reference to known or labeled outcomes. These learning methods are often more challenging to implement. Here the outcomes are subjective and there is no simple goal for the analysis. Unsupervised learning is part of exploratory data analysis. It can be hard to assess the results obtained from these methods, since there is no universally accepted way for validating the results. Unsupervised learning methods cannot be applied to regression or classification problem because we have no idea about the values of the output variable which makes it impossible to train the algorithm the way we do with ...