AI engineering glossary · Deep learning core
What is embedding layer?
Embedding layer: A layer that maps integer identifiers, such as word or item ids, to dense learnable vectors by table lookup. Similar items end up with similar vectors after training, giving the network a compact numeric representation of categories.
Embedding layer: an example
A vocabulary of 30,000 tokens with 256-dimensional embeddings is a 30,000 x 256 table of weights.
Related terms
More Deep learning core terms
- Epoch
- Evaluation mode
- Exploding gradient
- Exponential moving average of weights
- Fan-in and fan-out
- Feedforward neural network
- Flat minima
- Focal loss
Where you learn it
Embedding layer is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.