Skip to main content
🔒 Preview mode. The first 15 Foundations lessons are free; this one is Pro. Start a 7-day trial to unlock the editor, AI hints and the rest of the curriculum. Card required, cancel any time in Dashboard.
Start 7-day trial →
⚡
← Courses
›
Data Science Applied
›
Module 6 · Deep Learning + MLOps
›
Transformer: attention in one paragraph
quiz
90 / 104
🇺🇸
EN
▼
↗
Share
⋯
More
+100 XP
📋
Task
📖
Theory
🤖
AI Help
Task
📝 **Question:** Key advantage over RNN? 📋 Pick the right answer. 💡 **Hint:** Re-read the theory above if unsure.
🎯 Quiz
Question
📝 **Question:** Key advantage over RNN? 📋 Pick the right answer. 💡 **Hint:** Re-read the theory above if unsure.
A
Smaller parameter counts — attention layers share weights across positions, so a transformer needs fewer params than an RNN.
B
Parallelism + O(1) connection between any two tokens. RNN was sequential and forgot long-range info.
C
Better gradient flow — softmax outputs bounded values, so attention layers avoid the vanishing-gradient issue of LSTMs entirely.
D
Cheaper inference per token — attention's KV-cache lets you skip recomputing earlier states the way an RNN had to.
Submit answer
💬 Discussion
Be the first to ask a question or share a tip.
Sign in
to join the discussion. Reading is free.
Loading discussion…