370
edits
Vector embeddings: Difference between revisions
no edit summary
No edit summary |
|||
| (2 intermediate revisions by the same user not shown) | |||
| Line 51: | Line 51: | ||
Upon examining each of the 5 components of the vectors, it's evident that kitty and puppy are much closer than puppy and orange (we don't even have to determine the distances). Similarly, fruit is significantly closer to orange and blueberry compared to the other words, making them the top results for the "fruit" search. | Upon examining each of the 5 components of the vectors, it's evident that kitty and puppy are much closer than puppy and orange (we don't even have to determine the distances). Similarly, fruit is significantly closer to orange and blueberry compared to the other words, making them the top results for the "fruit" search. | ||
===More Than Just Words=== | ===More Than Just Words=== | ||
| Line 107: | Line 105: | ||
Even if embeddings are not directly used for an application, many popular machine learning models and methods rely on them internally. For instance, in [[encoder-decoder architectures]], the embeddings generated by the encoder contain the required information for the decoder to produce a result. This architecture is widely employed in applications like [[machine translation]] and [[caption generation]]. | Even if embeddings are not directly used for an application, many popular machine learning models and methods rely on them internally. For instance, in [[encoder-decoder architectures]], the embeddings generated by the encoder contain the required information for the decoder to produce a result. This architecture is widely employed in applications like [[machine translation]] and [[caption generation]]. | ||
===Products=== | |||
[[Vector database]] | |||
==Explain {{PAGENAME}} Like I'm 5 (ELI5)== | |||
Imagine you have a box of different toys like cars, dolls, and balls. Now, we want to sort these toys based on how similar they are. We can use something called "vector embedding" to help us with this. Vector embedding is like giving each toy a secret code made of numbers. Toys that are similar will have secret codes that are very close to each other, and toys that are not similar will have secret codes that are very different. | |||
For example, let's say we have a red car, a blue car, and a doll. We can give them secret codes like this: | |||
<poem style="border: 1px solid; padding: 1rem"> | |||
Red car: [1, 2, 3] | |||
Blue car: [1, 2, 4] | |||
Doll: [5, 6, 7] | |||
</poem> | |||
See how the red car and the blue car have secret codes that are very close to each other, while the doll has a different secret code? That's because the cars are more similar to each other than the doll. | |||
Vector embedding can also be used for words, pictures, sounds, and many other things. It helps computers understand and sort these things by how similar they are, just like we sorted the toys! | |||
[[Category:Terms]] [[Category:Artificial intelligence terms]] | [[Category:Terms]] [[Category:Artificial intelligence terms]] | ||