studying AI
Look this quote:
"An interesting feature of word embeddings is that because they’re numerical representations of contextual similarities between words, they can be manipulated arithmetically. The classic example is subtracting the ‘notion’ of “King” from “Man” and adding the notion of “Woman”. The answer will depend on your training set, but you’re likely to see one of the top results being the word “Queen”."
How I love linear algebra.
v.142857 /
npub16k…u4yu4
2023-05-01 11:58:47
Author Public Key
npub16k6pqaqza29zxuvl33lu2ln74wntc488ctdx9vunqqs8c9tf0rcsvu4yu4Published at
2023-05-01 11:58:47Event JSON
{
"id": "7c2b3a9266885c856635be2f15c4e8320d96f28e1b24fd5f0e8f9224b4e67b51",
"pubkey": "d5b4107402ea8a23719f8c7fc57e7eaba6bc54e7c2da62b39300207c156978f1",
"created_at": 1682942327,
"kind": 1,
"tags": [],
"content": "studying AI\n\nLook this quote:\n\n\"An interesting feature of word embeddings is that because they’re numerical representations of contextual similarities between words, they can be manipulated arithmetically. The classic example is subtracting the ‘notion’ of “King” from “Man” and adding the notion of “Woman”. The answer will depend on your training set, but you’re likely to see one of the top results being the word “Queen”.\"\n\nHow I love linear algebra.",
"sig": "9511aae1d9245b0f9195bf8a44018066259bcf47187208a77768976aa53ac65ad2d15714effc2029941cb1ec4d73c0879924fb1caf7825ad9c6194297c896d7a"
}