/
← L2: Types of Machine Learning L4: Unsupervised Learning →
Module 2: ML Foundation

L3: Supervised Learning

L3: Supervised Learning

24:19

Supervised learning is a type of machine learning where the algorithm is trained on labeled data. The training dataset includes both the input features and the corresponding correct outputs (labels). The goal of supervised learning is for the model to learn the relationship between the input and output so that it can make accurate predictions or classifications on new, unseen data.

There are two main types of supervised learning tasks:

  1. Regression : The goal is to predict continuous values. For example, predicting house prices based on features like size and location.

  2. Classification : The goal is to predict categorical labels. For example, classifying emails as "spam" or "not spam."

The key idea is that during training, the model makes predictions and is corrected based on the known outputs, gradually improving its accuracy over time.

Examples of supervised learning algorithms include:

  • Linear regression

  • Logistic regression

  • Decision trees

  • Support vector machines (SVM)

  • Neural networks

Supervised learning is often used in applications like image recognition, fraud detection, and sentiment analysis, where the data is labeled and the model's performance can be directly evaluated based on its predictions.