olemus
masinõppes: süvaõppe neurovõrgu kihtarhitektuur, mis võimaldab sisendjada osade rööptöötlust
Wiktionary:
3. (machine learning) a neural network architecture composed of layers of attention which takes sequences of tokens (representing text, images, audio, or other modalities) as input

ülevaateid
https://en.wikipedia.org/wiki/Transformer_(deep_learning_architecture)
https://aws.amazon.com/what-is/transformers-in-artificial-intelligence/
https://www.datacamp.com/tutorial/how-transformers-work
https://medium.com/@amanatulla1606/transformer-architecture-explained-2c49e2257b4c