# In the machine learning literature, what does it mean to say that something is “embedded” in some space?

In the machine learning literature, I often see it said that something is "embedded" in some space. For instance, that something is "embedded" in feature space, or that our data are "embedded" in dot product space, etc. However, I've never actually seen an explanation of what this is supposed to mean. So what does it actually mean to say that something is "embedded" in some space?

• Your question is different, but the answer can be found here. – nbro Dec 30 '20 at 20:04

The main reason behind using the embedding is doing meaningful mathematical computations in the target domain, which is not possible or straightforward in the source domain. For example, summing two words "brother" - "man" + "woman" not meaningful in the word and character levels. However, when using word2vec, embedding("brother") - embedding("man") + embedding("woman") can be meaningful and comparable with other embedded vectors; It should be near the embedded vector of "sister".