Errors in data are usually unwelcome and so some means to correct them is useful. However, it is difficult to define, detect or correct errors in an unsupervised way. Here, we train a deep neural network to re-synthesize its inputs at its output layer for a given class of data. We then exploit the fact that this abstract transformation, which we call a deep transform (DT), inherently rejects information (errors) existing outside of the abstract feature space. Using the DT to perform probabilistic re-synthesis, we demonstrate the recovery of data that has been subject to extreme degradation.
@article{arxiv.1502.04617,
title = {Deep Transform: Error Correction via Probabilistic Re-Synthesis},
author = {Andrew J. R. Simpson},
journal= {arXiv preprint arXiv:1502.04617},
year = {2015}
}