NPTEL Deep Learning – IIT Ropar Week 12 Assignment Answers 2025
1. What is the primary purpose of the attention mechanism in neural networks?
- To reduce the size of the input data
- To increase the complexity of the model
- To eliminate the need for recurrent connections
- To focus on specific parts of the input sequence
Answer :- For Answers Click Here
2. Which of the following are the benefits of using attention mechanisms in neural networks?
- Improved handling of long-range dependencies
- Enhanced interpretability of model predictions
- Ability to handle variable-length input sequences
- Reduction in model complexity
Answer :-
3. If we make the vocabulary for an encoder-decoder model using the given sentence. What will be the size of our vocabulary?
Sentence: Attention mechanisms dynamically identify critical input components, enhancing contextual understanding and boosting performance
- 13
- 14
- 15
- 16
Answer :-
4. We are performing the task of Machine Translation using an encoder-decoder model. Choose the equation representing the Encoder model.
- s0=CNN(xi)
- s0=RNN(st−1,e(y^t−1))
- s0=RNN(xit)
- s0=RNN(ht−1,xit)
Answer :-
5. Which of the following attention mechanisms is most commonly used in the Transformer model architecture?
- Additive attention
- Dot product attention
- Multiplicative attention
- None of the above
Answer :- For Answers Click Here
6. Which of the following is NOT a component of the attention mechanism?
- Decoder
- Key
- Value
- Query
- Encoder
Answer :-
7. In a hierarchical attention network, what are the two primary levels of attention?
- Character-level and word-level
- Word-level and sentence-level
- Sentence-level and document-level
- Paragraph-level and document-level
Answer :-
8. Which of the following are the advantages of using attention mechanisms in encoderdecoder models?
- Reduced computational complexity
- Ability to handle variable-length input sequences
- Improved gradient flow during training
- Automatic feature selection
- Reduced memory requirements
Answer :-
9. In the encoder-decoder architecture with attention, where is the context vector typically computed?
- In the encoder
- In the decoder
- Between the encoder and decoder
- After the decoder
Answer :-
10. Which of the following output functions is most commonly used in the decoder of an encoder-decoder model for translation tasks?
- Softmax
- Sigmoid
- ReLU
- Tanh
Answer :- For Answers Click Here
