One-hot encoding turns each item in a categorical set into a numerical vector: one position is 1, and every other position is 0. This gives an AI model a simple way to distinguish categories, but it is a coarse representation that can discard useful information. section 3.1.1
Representing words
For a vocabulary of words, each word receives its own vector position. The vector identifies the word through its single active element, without expressing richer relationships between words. section 3.1.1
Figure 3.4 One-hot encoding provides a simple numerical (algebraic) representation of words.
Use the figure to inspect how one-hot encoding provides a simple algebraic representation of words. section 3.1.1
