Machine Learning
Pembelajaran Mesin
Programs that improve from examples instead of hand-written rules.
Instead of a human writing every rule, the system is shown many examples and finds the pattern itself. A spam filter trained on millions of labelled emails learns what spam looks like; a recommendation model trained on watch history learns what you are likely to finish. The rules are still there, but nobody typed them. What changed from classical programming is where the logic comes from: from the programmer, or from the data.
Related terms
Deep Learning
Machine learning with many-layered networks that learn their own features.
Training
The expensive process that sets a model's parameters by exposing it to data.
Dataset
A collection of examples used to train, evaluate, or ground a system.
Supervised Learning
Learning from examples that come with the right answer attached.
Want this working inside your team?
It starts with one conversation about your workflow.