Explain about Denoising Autoencoder?

Ans: Generally, Autoencoders are used for Feature Selection and Feature Extraction. When the number of Hidden Layers is more than Input layers, then the output is equal to Input. To rectify this problem, we use Denoising Autoencoder.

Denoising Autoencoder corrupts the data by randomly making some of the input values to zero. In general, 50% of the Input nodes are set to zero. While calculating the Loss function, we have to compare Output values with the original input, not with the corrupted one. By doing this we can eliminate the risk of learning of identity function.

Denoising helps the autoencoders to learn the latent space representation present in the data. It ensures a good representation which can be derived robustly from a corrupted input and that will be useful for recovering the corresponding clean input.