layer_pseudo_embed: Create an Embedding Matrix
In tpq/caress: Caress, a Gentler Introduction to Keras

This function creates an embedding matrix in the form of a layer. This layer can be multiplied with other layers as if it were itself a weights matrix. This is because all samples within the embedding layer will always have the same activation.

1	layer_pseudo_embed(object, embed_dim, random_embedding = FALSE, name = NULL)

`object`	A `keras` model.
`embed_dim`	An integer. The size of the final embedding matrix will equal the input dimension times the embedding dimension.
`random_embedding`	A boolean. Toggles whether to freeze the embedding matrix with random values. Otherwise, the embedding matrix is trainable.
`name`	A string. The prefix label for all layers.