Machine learning is a type of Artificial Intelligence (AI) that predicts an outcome based on unseen variables. Machine learning models take an input $X$ and map it to an output $Y$ based on some function, i.e., $Y = f(X)$.
There are mainly two types of machine learning models: supervised and unsupervised.
Supervised models make use of labeled datasets to predict outcomes, while unsupervised models work on datasets that are not explicitly labeled. Supervised models can further be categorized as regression or classification models.
Regression models map inputs onto continuous outputs.
Linear regression: This type of regression model includes a line of best fit (linear regression) or a curve of best fit (polynomial regression).
Decision tree: Trees are used to predict outcomes, with each tree node representing a decision. The more nodes a tree has, the more accurate the outcome is. The leaves of the tree represent the outcome.
Neural network: This model predicts outcomes based on a set of known variables that pass through several equations. The input variables are the input layer, which pass through hidden layers in which each node represents a function. The outcomes are found in the output layer.
Classification models have discrete outputs, which means that input variables are mapped to fixed outcomes.
Logistic regression: The most used classification model is logistic regression, where the output can be either 1 or 0.
Support vector machine: This classification model places a boundary between different data classes that maximize the margin between them. For example, a linear support vector machine draws a straight boundary that distinguishes between two classes.
RELATED TAGS
CONTRIBUTOR
View all Courses