Feature: Difference between revisions

1,002 bytes added ,  20 February 2023
no edit summary
No edit summary
No edit summary
Line 1: Line 1:
{{see also|Machine learning terms}}
==Introduction==
==Introduction==
[[Feature]] is an [[input]] variable to a [[machine learning model]]. An [[example]] consists of 1 or more features.
[[Feature]] is an [[input]] variable to a [[machine learning model]]. An [[example]] consists of 1 or more features.
Line 51: Line 52:


Feature engineering can involve several techniques, such as [[scaling]], [[normalization]], [[binning]], [[one-hot encoding]] of polynomial features and interaction terms. The purpose is to extract the most informative signal from data while reducing noise and redundancy within features.
Feature engineering can involve several techniques, such as [[scaling]], [[normalization]], [[binning]], [[one-hot encoding]] of polynomial features and interaction terms. The purpose is to extract the most informative signal from data while reducing noise and redundancy within features.
==Explain Like I'm 5 (ELI5)==
Machine learning works like this: features are like cues that assist the computer in discovering something.
Imagine playing a guessing game with your friend where they must guess which animal you are thinking of. You might provide some clues such as "it has fur" or "it's really big." These features act like cues to help them identify which animal it is you have in mind.
Machine learning involves providing features to a computer so it can learn about something, like pictures of animals. We might give the computer cues such as "it has four legs" or "it has pointy ears." These cues help the machine recognize which animal is in a picture quickly and accurately.
By giving the computer numerous features, it can learn to recognize patterns in data and make predictions on its own. It's like how you can guess what animal your friend is thinking of based on clues provided.
[[Category:Terms]] [[Category:Machine learning terms]]