|
|
| Line 30: |
Line 30: |
|
| |
|
| Sometimes, we must adjust information slightly so the computer can better comprehend it. For instance, if we want to determine which neighborhood a house is in, we might change its name from "Brooklyn" to something simpler like "1 or 2," making it simpler for the computer to process and utilize this data when making predictions. | | Sometimes, we must adjust information slightly so the computer can better comprehend it. For instance, if we want to determine which neighborhood a house is in, we might change its name from "Brooklyn" to something simpler like "1 or 2," making it simpler for the computer to process and utilize this data when making predictions. |
|
| |
| ==Explain Like I'm 5 (ELI5)==
| |
| Sure! Picture a toy box filled with many toys. Each toy has unique features or qualities that set it apart, like four wheels, doors that open, and a steering wheel - these characteristics are like what machine learning experts refer to as "attributes."
| |
|
| |
| Machine learning uses attributes to describe things and make things clearer. Just as wheels, doors, and steering wheel help us know what a toy car is, attributes provide guidance for our computer program so it knows what things need to be taken care of in order for it to make decisions or solve problems more efficiently.
| |
|
| |
| Therefore, an attribute is simply a feature or characteristic that helps us better describe and comprehend something!
| |
|
| |
| ==Explain Like I'm 5 (ELI5)==
| |
| Machine learning utilizes attributes, which are like discrete pieces of information about something we want to study or predict. For instance, if we want to determine whether it will rain tomorrow morning, we might look at factors like temperature, humidity and wind speed.
| |
|
| |
| Attributes come in many forms, like numbers or words, that we can use to make predictions. Sometimes it's necessary to modify these attributes for improved usability or usefulness - this process is called feature engineering. Selecting the correct attributes is crucial for making accurate predictions!
| |
|
| |
| ==Explain Like I'm 5 (ELI5)==
| |
| Hey there! Have you ever played with a toy that has different parts, like a car with wheels and body, plus stickers or decorations? Each part has something special about it that sets it apart from the others, right?
| |
|
| |
| Machine learning uses attributes, similar to parts of a toy - these are things we measure or describe about something. Attributes provide context and help us better understand something's behavior.
| |
|
| |
| Let us say we want to teach a computer how to distinguish different kinds of fruit. We could measure attributes such as color, size, shape and texture from each fruit in order to teach it how to tell the difference between an apple and orange or between banana and strawberry.
| |
|
| |
| Just as different parts of a toy have their own distinct qualities, attributes help us decipher and distinguish things in machine learning!
| |
|
| |
|
|
| |
|
| [[Category:Terms]] [[Category:Machine learning terms]] [[Category:Not Edited]] | | [[Category:Terms]] [[Category:Machine learning terms]] [[Category:Not Edited]] |
