NPTEL Deep Learning – IIT Ropar Week 6 Assignment Answers 2025
1. What is/are the primary advantages of Autoencoders over PCA?
- Autoencoders are less prone to overfitting than PCA.
- Autoencoders are faster and more efficient than PCA.
- Autoencoders require fewer input data than PCA.
- Autoencoders can capture nonlinear relationships in the input data.
Answer :- For Answers Click Here
2. Which of the following is a potential advantage of using an overcomplete autoencoder?
- Reduction of the risk of overfitting
- Faster training time
- Ability to learn more complex and nonlinear representations
- To compress the input data
Answer :-
3. We are given an autoencoder A. The average activation value of neurons in this network is 0.015. The given autoencoder is
- Contractive autoencoder
- Sparse autoencoder
- Overcomplete neural network
- Denoising autoencoder
Answer :-
4. Suppose we build a neural network for a 5-class classification task. Suppose for a single training example, the true label is [0 1 0 0 1] while the predictions by the neural network are [0.4 0.25 0.2 0.1 0.6]. What would be the value of cross-entropy loss for this example? (Answer up to two decimal places, Use base 2 for log-related calculations)
Answer :-
5. If an under-complete autoencoder has an input layer with a dimension of 5, what could be the possible dimension of the hidden layer?
- 5
- 4
- 2
- 0
- 6
Answer :-
6. Which of the following networks represents an autoencoder?
Answer :- For Answers Click Here
7. What is the primary reason for adding corruption to the input data in a denoising autoencoder?
- To increase the complexity of the model.
- To improve the model’s ability to generalize to unseen data.
- To reduce the size of the training dataset.
- To increase the training time.
Answer :-
8. Suppose for one data point we have features x1,x2,x3,x4,x5 as −4,6,2.8,0,17.3 then, which of the following function should we use on the output layer(decoder)?
- Linear
- Logistic
- Relu
- Tanh
Answer :-
9. Which of the following statements about overfitting in overcomplete autoencoders is true?
- Reconstruction error is very high while training
- Reconstruction error is very low while training
- Network fails to learn good representations of input
- Network learns good representations of input
Answer :-
10. What is the purpose of a decoder in an autoencoder?
- To reconstruct the input data
- To generate new data
- To compress the input data
- To extract features from the input data
Answer :- For Answers Click Here
