HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Gated Autoencoders with Tied Input Weights

Abstract : The semantic interpretation of images is one of the core applications of deep learning. Several techniques have been recently proposed to model the relation between two images, with application to pose estimation, action recognition or invariant object recognition. Among these techniques, higher-order Boltzmann machines or relational autoencoders consider projections of the images on different subspaces and intermediate layers act as transformation specific detectors. In this work, we extend the mathematical study of (Memisevic, 2012b) to show that it is possible to use a unique projection for both images in a way that turns intermediate layers as spectrum encoders of transformations. We show that this results in networks that are easier to tune and have greater generalization capabilities.
Document type :
Conference papers
Complete list of metadata

Cited literature [19 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00817035
Contributor : Alain Droniou Connect in order to contact the contributor
Submitted on : Tuesday, April 23, 2013 - 3:47:49 PM
Last modification on : Saturday, January 22, 2022 - 3:01:52 AM
Long-term archiving on: : Thursday, July 25, 2013 - 11:27:06 AM

File

icml2013_gated_autoencoders.pd...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00817035, version 1

Citation

Alain Droniou, Olivier Sigaud. Gated Autoencoders with Tied Input Weights. International Conference on Machine Learning, 2013, United States. ⟨hal-00817035⟩

Share

Metrics

Record views

169

Files downloads

198