## NPTEL Deep Learning – IIT Ropar Week 6 Assignment Asnwers 2024

1. Which of the following networks represents an autoencoder?

Answer :-For Answers Click Here

2. If an under-complete autoencoder has an input layer with a dimension of 7, what could be the possible dimension of the hidden layer?

- 6
- 8
- 0
- 7
- 2

Answer :-For Answers Click Here

3. What type of autoencoder is it when the hidden layerâ€™s dimensionality is less than that of the input layer?

- Under-complete autoencoder
- Complete autoencoder
- Overcomplete autoencoder
- Sparse autoencoder

Answer :-For Answers Click Here

4. Which of the following statements about regularization in autoencoders is always true?

- Regularisation reduces the search space of weights for the network.
- Regularisation helps to reduce the overfitting in overcomplete autoencoders.
- Regularisation shrinks the size of weight vectors learned.
- All of these.

Answer :-

5. We are using the following autoencoder with linear encoder and linear decoder. The eigenvectors associated with the covariance matrix of our data X is (V_{1},V_{2},V_{3},V_{4},V_{5}). What are the representations most likely to be learned by our hidden layer H? (Eigenvectors are written in decreasing order to the eigenvalues associated with them)

- V
_{1},V_{2} - V
_{4},V_{5} - V
_{1},V_{3} - V
_{1},V_{2},V_{3},V_{4},V_{5}

Answer :-

6. 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

7. What are the advantages of using a denoising autoencoder?

- Robustness to noisy input data
- Reduction of the risk of overfitting
- Faster training time
- It promotes sparsity in the hidden layer

Answer :-

8. We are given an autoencoder A. The average activation value of neurons in this network is 0.06. The given autoencoder is:

- Contractive autoencoder
- Overcomplete neural network
- Sparse autoencoder
- Denoising autoencoder

Answer :-

9. What are the possible applications of autoencoders?

- Data Compression
- Extraction of important features
- Reducing noise
- All of these

Answer :-

10. Which of the following is a potential disadvantage of using autoencoders for dimensionality reduction over PCA?

- Autoencoders are computationally expensive and may require more training data than PCA.
- Autoencoders are bad at capturing complex relationships in data
- Autoencoders may overfit the training data and generalize poorly to new data.
- Autoencoders are unable to handle linear relationships between data.

Answer :-For Answers Click Here