AI Foundations
Machine learning
ML
A way of building software that learns patterns from data instead of following only hand-written rules.
Two ways to build it
Hand-written rules
- A person writes rules
- The rules are fixed
- Software follows them
Machine learning
- It is shown examples
- It finds a pattern
- It applies that pattern
Example
A fraud system learns patterns from past card transactions instead of relying only on fixed rules.
Why it matters
It helps tackle problems where writing a separate rule for every situation would be impractical.
You'll hear it
“We taught it using examples from our earlier work.”
Can you control it?
Set by the team
The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.
Common questions
- Can a useful pattern stop working later?
- Yes. People's behavior or surrounding conditions can change, making an earlier pattern less reliable.
- Does machine learning keep learning while I use it?
- Usually not. Many systems use a fixed trained model until the provider trains or updates it again.
- Is machine learning always AI?
- Machine learning is generally treated as a branch of AI, but not every AI system uses machine learning.