Autoencoders in DL

Select the correct option.
A. Supervised learning methods include autoencoders.
B. The output and input of the autoencoder are identical.

• 1. Both the statements are TRUE.

• 1. Statement A is TRUE, but statement B is FALSE.

• 1. Statement A is FALSE, but statement B is TRUE.

• 1. Both the statements are FALSE.

Select the correct option about Denoising autoencoders.
A. The loss is between the original input and the reconstruction from a noisy version of the input.
B. Denoising autoencoders can be used as a tool for feature extraction.

• 1. Both the statements are TRUE.

• 1. Statement A is TRUE, but statement B is FALSE.

• 1. Statement A is FALSE, but statement B is TRUE.

• 1. Both the statements are FALSE

How many layers are there in Autoencoder?

• 1

• 2

• 3

• 4

Select the correct option about Sparse autoencoders.
A. Sparse autoencoders introduces information bottleneck by reducing the number of nodes
at hidden layers.
B. The idea is to encourage network to learn an encoding and decoding which only relies on
activating a small number of neurons.

• 1. Both the statements are TRUE.

• 1. Statement A is TRUE, but statement B is FALSE.

• 1. Statement A is FALSE, but statement B is TRUE.

• 1. Both the statements are FALSE.

De-noising and Contractive are examples of

• 1. Shallow Neural Networks

• 1. Recurrent Neural Networks

• 1. Convolution Neural Networks

• 1. Autoencoders

The rate at which cost changes with respect to weight or bias is called ___________

• Derivative

• Gradient

• Loss

• Rate of change

Prediction accuracy of a neural network depends on __________ and ________

• input and output

• weight and bias

• linear and logistic

• activation and threshold

Autoencoders cannot be used for Dimensionality Reduction.

• True

• False

• May be

• Cannot say

______________ is a recommended model for pattern recognition in unlabelled data

• CNN

• RNN

• Autoencoders

• Shallow neural networks

Autoencoders are trained without supervision.

• True

• False

• Cannot be predicted

• may be