At Data Science Dojo, our mission is to make data science (machine learning in this case) available to everyone.
Machine learning is the subfield of computer science that "gives computers the ability to learn without being explicitly programmed" (Arthur Samuel, 1959). Evolved from the study of pattern recognition and computational learning theory in artificial intelligence, machine learning explores the study and construction of algorithms that can learn from and make predictions on data. In this blog post, we are going to be looking at three areas of machine learning and share an interactive infographic to classify different techniques.
Supervised Machine Learning
Supervised machine learning models use a dataset that has target values or labels to predict the target values or labels in a dataset for which labels are not known. Long story short, we give the supervised model a dataset with the answers (labels) so that it can learn how to predict the label(s) for other examples where the labels are unknown.
Reinforcement Learning
Reinforcement learning, on the other hand, is not trained with the answer. Instead, an agent is either penalized or rewarded for interacting with the environment. It learns from previous attempts and tries to maximize the reward with each attempt.
Unsupervised Machine Learning
Unsupervised machine learning algorithms find hidden structures between the attributes or features when the given dataset does not include labels. This is different than supervised learning in that we don't tell the model what it needs to learn. The unsupervised model is given inputs that it must use to identify hidden structures and patterns to draw conclusions.
This is a companion discussion topic for the original entry at https://blog.datasciencedojo.com/p/b07e0621-61dc-484b-91fb-79d1043ffdbe/