¡Hola, Mundo!

AIM encoding : Identifying relativity between each data embedding : Numerical vectorization encoding The acquisition of vector that enables distinguish and numerically meaningful. For example, 'wonderful, beautiful = Seoul' If it can be quantifid, it can be bectorized as below. (10, 6) = Seoul Now, in this way, each cities can be expressed based on 'wonderful' and 'beautiful', and this allows us..

text encoding text -> integer ex) [2,4,6,1] It can be said 'input ids' after convert to integer. text decoding integer -> text embedding (1d)text encoding -> (2d)vector ex) [[2,4,6,1]] data input ids, vector trainable parameters embedding layer, attention encoder, attention decoder