Understanding Supervised, Unsupervised, and Reinforcement Learning in Machine Learning with Example
Machine Learning is a subset of artificial intelligence that focuses as developing algorithms and statistical model that can allow computers to learn from data and make prediction or decision based on data without being explicitly programmed as well as allows the model to improve it’s performance by learning from the new data. A common example of machine learning would be a spam filter, initially trained on labeled examples of spam and non-spam emails flagged by users.
There are three major type of machine learning algorithms: supervised learning, unsupervised learning, and reinforcement learning. Understanding these concepts is essential for anyone starting their machine learning journey. In this article, we’ll break down what they are, explore some common algorithms, and provide real-world examples to help you grasp the concepts.
What is Supervised Learning?
Supervised learning can be considered as tutoring a young student. You give the model (the “student”) a set of labeled examples (the “lessons”) to learn from. The model’s job is to learn how to map inputs to the correct outputs by utilizing these prelabelled input data (features) and the correct output (label) data.
