#residual-connections

3 questions from Attention & Transformers, Landmark Architectures

Timed test

3 questions · 3 min · score and explanations at the end

Q 1 / 3Score 0 / 0

Shuffle questions

Question 1: Select all that apply

easyAI-checkedAttention & Transformers

Which of these are typical components of a transformer block? Select all that apply.

A multi-head self-attention layer1
A feedforward layer applied to each token separately2
Residual connections and layer normalization3
A recurrent connection that passes a hidden state from one token to the next4
A pooling layer that halves the sequence length after each block5

Keys: 1–9 select · Enter check / next