Machine Learning Algorithms
Explore the essential machine learning algorithms including regression, classification, and clustering. Understand how these algorithms work, their practical use cases, and how to select the best approach for different AI problems. This lesson helps build foundational ML knowledge crucial for AWS AI Practitioner certification preparation.
We have already learned about the three broadly classified ML techniques: supervised, unsupervised, and reinforcement learning. Let's dive in and learn about the types of ML algorithms.
Regression
Regression in machine learning analyzes how independent variables or features correlate with a dependent variable or outcome. It serves as a predictive modeling approach, where an algorithm predicts continuous outcomes.
Consider an example where we want to predict the house price using only its area. We can model this using a straight line that describes the relationship between an area (independent variable) and the price of the house (dependent variable).
However, the house price depends on various other factors, such as the number of rooms and the locality of the house. In such cases, we can use multi-regression to model the dependency of the house price on multiple independent variables.
Regression is not limited to linear relationships. We can use non-linear regressions, such as polynomial regression, logistic regression, etc, to predict the target variable.
Common regression examples
Other common examples of regression use cases include: