AI engineering glossary · NLP embeddings
What is siamese network?
Siamese network (also called Twin network): A neural architecture that passes two inputs through the same network with shared weights and then compares the outputs. It is trained so that similar pairs land close together and dissimilar pairs land far apart.
Siamese network: an example
Two job descriptions are encoded by the same network, and their vectors are compared to decide if they describe the same role.
Related terms
More NLP embeddings terms
- Skip-gram
- Slot filling
- Smoothing
- spaCy
- Special tokens
- Spelling correction
- Static embedding
- Subword regularisation
Where you learn it
Siamese network is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.