Java: Data Science Made Easy

Specialized autoencoders

There are specialized versions of autoencoders. When an autoencoder uses more hidden layers than inputs, it may learn the identity function, which is a function that always returns the same value used as input to the function. To avoid this problem, an extension to the autoencoder, denoising autoencoder, is used; it randomly modifies the input introducing noise. The amount of noise introduced varies depending on the input dataset. A Stacked Denoising Autoencoder (SdA) is a series of denoising autoencoders strung together.