Supervised learning is a common type of machine learning. In this video, learn how to set an algorithm with a matrix and a target vector to make predictions.
- [Instructor] The most common form of machine learning is supervised learning. In Scikit-Learn, a supervised learning algorithm learns a relationship between your features matrix and your target factor. A feature is a measurable property. A target is typically what you want to make predictions for. Once a model learns a relationship between a features matrix and a target factor, it can make predictions for unseen or future data. Supervised learning can generally be thought of to solve two different types of tasks. The first is when you try to predict a continuous value. This is considered a regression problem. This means that your target factor contains continuous qualities like home prices. The second is when you're trying to predict a categorical value. This is considered a classification problem. This means that your target factor contains categorical values like different flower species. So that's it. Supervised learning is when an algorithm learns from a features matrix and target factor to make predictions.
This course was created by Madecraft. We are pleased to host this content in our library.
- Why use scikit-learn?
- Supervised vs. unsupervised learning
- Linear and logistic regression
- Decision trees and random forests
- K-means clustering
- Principal component analysis (PCA)