Bird
0
0

How do you correctly add an LSTM layer with 100 units in a Keras Sequential model for text input of shape (timesteps, features)?

easy📝 Syntax Q3 of 15
NLP - Sequence Models for NLP
How do you correctly add an LSTM layer with 100 units in a Keras Sequential model for text input of shape (timesteps, features)?
Amodel.add(LSTM(100, input_shape=(timesteps, features)))
Bmodel.add(LSTM(100, input_dim=timesteps, input_length=features))
Cmodel.add(LSTM(units=timesteps, input_shape=(100, features)))
Dmodel.add(LSTM(100, input_shape=(features, timesteps)))
Step-by-Step Solution
Solution:

  1. Step 1: Understand input_shape

    For LSTM, input_shape is (timesteps, features).

  2. Step 2: Correct syntax

    Use LSTM(units, input_shape=(timesteps, features)) in Keras Sequential.

  3. Final Answer:

    model.add(LSTM(100, input_shape=(timesteps, features))) -> Option A

  4. Quick Check:

    Check input_shape format [OK]
Quick Trick: LSTM input_shape = (timesteps, features) [OK]
Common Mistakes:
MISTAKES
  • Swapping timesteps and features in input_shape
  • Using input_dim or input_length incorrectly
  • Setting units to timesteps

Want More Practice?

15+ quiz questions · All difficulty levels · Free

Free Signup - Practice All Questions
More NLP Quizzes
Sentiment Analysis Advanced - Aspect-based sentiment analysis - Quiz 10hard Sentiment Analysis Advanced - Hybrid approaches - Quiz 1easy Sentiment Analysis Advanced - Why advanced sentiment handles nuance - Quiz 13medium Sentiment Analysis Advanced - Fine-grained sentiment (5-class) - Quiz 11easy Sequence Models for NLP - Why sequence models understand word order - Quiz 4medium Sequence Models for NLP - Padding and sequence length - Quiz 9hard Sequence Models for NLP - Attention mechanism basics - Quiz 4medium Topic Modeling - Latent Dirichlet Allocation (LDA) - Quiz 4medium Word Embeddings - Word similarity and analogies - Quiz 10hard Word Embeddings - Visualizing embeddings (t-SNE) - Quiz 10hard