On the contractive nature of autoencoders: application to missing sensor restoration

The neural network autoencoder is a useful tool for the restoration of missing sensors when enough known sensors with some relation to those missing are available. Through the idea of a contraction mapping, this paper provides some insight into the convergence of several iterative methods of sensor restoration using the autoencoder to some unique answer given a specific operating point (i.e., the known sensor values), regardless of how the missing sensor values are initialized.