Skip to content
BENIBIX Learn

Machine Learning

Also known as ML

A way to build AI. The computer learns the rules from data. People do not write them.

Think of it like

Think of it like a kid who sees lots of dogs. Soon the kid can spot a dog.

Example

Lucy's email service shows a model 100,000 emails marked spam or not spam. It learns the signs of spam and now sorts new mail by itself.

Why it matters

Almost all AI today is built this way. It works on jobs where the rules are too many for anyone to write down.

Definition

Machine learning is a way to build AI where the computer learns from examples. People do not write the rules by hand. They give the computer lots of data and the right answers. The computer finds the patterns that link them. Then it uses those patterns on new data it has never seen.
Machine learning is the middle circle. It is one part of AI, and deep learning is one part of it.

Common mistake

Thinking machine learning and AI are the same thing. Machine learning is one way to build AI, and today it is the main one.

Key takeaways

  1. 1
    Learns from data. Not from rules people write.
  2. 2
    Finds patterns. Links the data to the answers.
  3. 3
    Works on new data. Uses what it learned on new cases.

Compare

Learn it properly