Machine learning
Programming by example — you show the computer data instead of writing the rules yourself.
Think of it like
Training a dog with treats rather than handing it an instruction manual.
Example
A spam filter that learns from which emails you mark as junk is machine learning; a fixed “block anything with FREE MONEY” rule is not.
How it actually works
Instead of a human coding logic step by step, an algorithm adjusts its own parameters to fit patterns in data. Give it examples, it finds the mapping. The catch: it’s only as good, and as biased, as the data you feed it.
For product teams
It shines when rules are too messy to write by hand but examples are plentiful.
For engineers
Algorithms that improve on a task by optimizing parameters against data, rather than via explicit programming.
Related
- Deep learning — A subfield is deep learning.
- Artificial intelligence — The umbrella above it is artificial intelligence.
Read anything AI without the jargon
Look up any term in plain English, or save terms as you read with the free Chrome extension.
Open DecoderAdd to Chrome