NPTEL Deep Learning – IIT Ropar Week 11 Assignment Answers 2025
1. For which of the following problems are RNNs suitable?
- Generating a description from a given image.
- Forecasting the weather for the next N days based on historical weather data.
- Converting a speech waveform into text.
- Identifying all objects in a given image.
Answer :- For Answers Click Here
2. Suppose that we need to develop an RNN model for sentiment classification. The input to the model is a sentence composed of five words and the output is the sentiments (positive or negative). Assume that each word is represented as a vector of length 100×1 and the output labels are one-hot encoded. Further, the state vector st is initialized with all zeros of size 30×1. How many parameters (including bias) are there in the network?
Answer :-
3. Select the correct statements about GRUs
- GRUs have fewer parameters compared to LSTMs
- GRUs use a single gate to control both input and forget mechanisms
- GRUs are less effective than LSTMs in handling long-term dependencies
- GRUs are a type of feedforward neural network
Answer :-
4. What is the main advantage of using GRUs over traditional RNNs?
- They are simpler to implement
- They solve the vanishing gradient problem
- They require less computational power
- They can handle non-sequential data
Answer :-
5. The statement that LSTM and GRU solves both the problem of vanishing and exploding gradients in RNN is
- True
- False
Answer :- For Answers Click Here
6. What is the vanishing gradient problem in training RNNs?
- The weights of the network converge to zero during training
- The gradients used for weight updates become too large
- The network becomes overfit to the training data
- The gradients used for weight updates become too small
Answer :-
7. What is the role of the forget gate in an LSTM network?
- To determine how much of the current input should be added to the cell state.
- To determine how much of the previous time step’s cell state should be retained.
- To determine how much of the current cell state should be output.
- To determine how much of the current input should be output.
Answer :-
8. How does LSTM prevent the problem of vanishing gradients?
- Different activation functions, such as ReLU, are used instead of sigmoid in LSTM.
- Gradients are normalized during backpropagation.
- The learning rate is increased in LSTM.
- Forget gates regulate the flow of gradients during backpropagation.
Answer :-
9.
Answer :-
10. Select the true statements about BPTT?
- The gradients of Loss with respect to parameters are added across time steps
- The gradients of Loss with respect to parameters are subtracted across time steps
- The gradient may vanish or explode, in general,if timesteps are too large
- The gradient may vanish or explode if timesteps are too small
Answer :- For Answers Click Here
