Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Revisiting Denoising Auto-Encoders
Luis Gonzalo Sanchez Giraldo
Nov 05, 2016 (modified: Dec 15, 2016)ICLR 2017 conference submissionreaders: everyone
Abstract:Denoising auto-encoders (DAE)s were proposed as a simple yet powerful way to obtain representations in an unsupervised manner by learning a map that approximates the clean inputs from their corrupted versions. However, the original objective function proposed for DAEs does not guarantee that denoising happens only at the encoding stages. We argue that a better representation can be obtained if the encoder is forced to carry out most of the denoising effort. Here, we propose a simple modification to the DAE's objective function that accomplishes the above goal.
TL;DR:Modified objective for denoising autoencoders with explicit robustness in the encoding.
Enter your feedback below and we'll get back to you as soon as possible.