Quiz · 5 questions
📝 Sequences, RNNs & Attention
From SimpleRNN to LSTM to Multi-Head Attention — and why we got here
Level 0Level 0
0 XP0/78 lessons0/17 achievements
0/100 XP to next level100 XP to go0% complete
Quiz
01Why does a stacked LSTM need return_sequences=True on all but the last layer?
02Why does GRU train faster than LSTM with similar accuracy?
03What's the architectural reason Transformers outperform LSTMs on long sequences?
04What does merge_mode='concat' do in a Bidirectional LSTM wrapper?
05Why include TextVectorization inside the model rather than preprocessing text separately?
Comments 0
🔔 Reply notifications (sign in)Sign in — Please sign in to comment.
No comments yet — be the first.