Machine Learning Basics

Machine learning teaches a computer to recognize patterns in examples. The result is a model that can make useful predictions on new data.

How a model learns

A dataset contains examples. Each example may include features—measurements such as price, size, or word count—and sometimes a label, the answer we want the model to learn.

During training, an algorithm adjusts the model so its predictions become closer to known answers. We then test it on unseen data to check whether it learned a general pattern.

Common learning styles

• Supervised: examples include the correct label.
• Unsupervised: the model finds structure without labels.
• Reinforcement: an agent learns through feedback and rewards.

Example

const examples = [{ hours: 1, score: 55 }, { hours: 2, score: 65 }];
const predictedScore = 45 + (hours * 10);