Skip to main content
Cross Validated

Return to Question

Bumped by Community user
Bumped by Community user
Bumped by Community user
fixed accronyms
Source Link
edit approved Dec 5, 2016 at 12:40
Seanny123
edit approved Dec 5, 2016 at 12:40
Seanny123
  • 667
  • 4
  • 21

DAEDenoising Autoencoders (DAE) works by inducing some noise in the input vector and then transforming it into the hidden layer, while trying to reconstruct the original vector. However, I fail to understand the intuition of contractive autoencodersContractive Autoencoders (CAE).

Does the CAE say that the hidden layer will only learn the features that differentiate one input from the rest of the inputs in a vector? If so then how would we reconstruct the original vector?

DAE works by inducing some noise in the input vector and then transforming it into the hidden layer, while trying to reconstruct the original vector. However, I fail to understand the intuition of contractive autoencoders.

Does the CAE say that the hidden layer will only learn the features that differentiate one input from the rest of the inputs in a vector? If so then how would we reconstruct the original vector?

Denoising Autoencoders (DAE) works by inducing some noise in the input vector and then transforming it into the hidden layer, while trying to reconstruct the original vector. However, I fail to understand the intuition of Contractive Autoencoders (CAE).

Does the CAE say that the hidden layer will only learn the features that differentiate one input from the rest of the inputs in a vector? If so then how would we reconstruct the original vector?

Source Link
Arslán
Arslán
  • 579
  • 8
  • 13

What is the difference between denoising autoencoder and contractive autoencoder?

DAE works by inducing some noise in the input vector and then transforming it into the hidden layer, while trying to reconstruct the original vector. However, I fail to understand the intuition of contractive autoencoders.

Does the CAE say that the hidden layer will only learn the features that differentiate one input from the rest of the inputs in a vector? If so then how would we reconstruct the original vector?