This is my first blog and it is all about supervised learning and unsupervised learning. Let us first look into what Machine learning is. Machine learning is a specially designed technology that comes under Artificial Intelligence (AI). As you all know, machine learning is playing a vital role in the current scenario in most of the organizations in order to provide required services and functions. Right from e-commerce websites, self-driving cars, finance, healthcare and social media platforms, etc., machine learning methods are used to carry out various functions or operations with the help of variety of data.
Based on the availability of data or datasets and their uses, machine learning is subdivided into two different methods namely,
Supervised learning Unsupervised learning
Classification Clustering Anomaly
What is Supervised learning?
Supervised learning processes labelled input and output data in order to process the function. As the name suggests, this type of learning involves human supervision to at least a part of the function/project. In simple terms, to group a familiar data or a known data. Supervised learning can be grouped into Classification.
Examples of classification - Classification of Cars; labelling of emails (promotions, spam, updates, etc.,).
What is Unsupervised learning?
Unsupervised learning process unlabeled or raw data. The reason it is called unsupervised learning is that it does not involve human interaction compared to supervised machine learning. In a nutshell, the vast majority of available data is unlabeled and raw data. By grouping data with similar features and their applications, unsupervised learning can be grouped into Clustering & Anomaly.
Clustering is when similar or different datasets are grouped together.
Examples: People with same interests join a training/program together; Two wheelers & Four Wheelers.
Anomaly is identification of rare items or data which completely differ from the standards.
Examples: Zebra among animals; Ostrich among birds; Jackfruit among fruits.