📚 Learning Guide
Transformer Architecture
hard

Attention:Encoder :: Decoder:?

Master this concept with our detailed explanation and step-by-step learning approach

Learning Path
Learning Path

Question & Answer
1
Understand Question
2
Review Options
3
Learn Explanation
4
Explore Topic

Choose the Best Answer

A

Attention

B

Context

C

Output

D

Input

Understanding the Answer

Let's break down why this is correct

Answer

In a transformer, the encoder uses self‑attention to let each token look at every other token in the input. The decoder also uses self‑attention, but it is masked so that a token can only attend to previous tokens, preventing it from peeking ahead. In addition, the decoder has a second attention layer that lets each token attend to the encoder’s output; this is the encoder‑decoder (cross) attention. Thus the decoder’s attention mechanisms are masked self‑attention plus cross‑attention, mirroring the encoder’s self‑attention but adapted for generation.

Detailed Explanation

The decoder’s main job is to create the next word in the output sequence. Other options are incorrect because The attention part is a tool inside the decoder, not the thing the decoder produces; Context is what the decoder receives from the encoder, not what it creates.

Key Concepts

Transformer Architecture
Attention Mechanism
Sequence Generation
Topic

Transformer Architecture

Difficulty

hard level question

Cognitive Level

understand

Ready to Master More Topics?

Join thousands of students using Seekh's interactive learning platform to excel in their studies with personalized practice and detailed explanations.