What Does Learning Algorithm Mean?
A learning algorithm is a set of instructions used in machine learning that allows a computer program to imitate the way a human gets better at characterizing some types of information. The math and logic that supports a learning algorithm can update itself over time (without human intervention) as the programming becomes exposed to more data.
Learning algorithms are useful in both supervised and unsupervised machine learning, but they are each used in different ways. Supervised learning algorithms require training data to be labeled, while unsupervised learning algorithms look for patterns to characterize input.
In general, what all learning algorithms have in common is their ability to extrapolate information from training data and use what they learn to make predictions about new input.
Techopedia Explains Learning Algorithm
Examples of learning algorithms include logic regression, linear regression, decision trees and random forests.
- Logic regressions are used to obtain an odds ratio in the presence of more than one variable.
- Linear regressions are used to study the relationship between a dependent variable and one or more independent variables.
- Decision trees are used to split input data recursively based on input features.
- Random forests are used to divide input data into homogeneous groups.
- Lazy learning algorithms like K-nearest neighbor also support decision-making in machine learning programs.
The bottom line is that machine learning engineers use learning algorithms as building blocks to help AI programs understand and work with the data they are given.