CertBrain
Courses
Home
Blog
Sign in
← Transformers, Foundation Models and Diffusion Models
1 / 10
Question
Which feature of the transformer architecture lets it weigh how every word in a sentence relates to every other word?
1
Self-attention
2
Gradient boosting across many small models
3
Decision trees that split the text into branches
4
Convolution filters that slide across the text
Press 1–4 to pick an answer