On Nonparametric Guidance for Learning Autoencoder Representations

DSpace/Manakin Repository

On Nonparametric Guidance for Learning Autoencoder Representations

Citable link to this page


Title: On Nonparametric Guidance for Learning Autoencoder Representations
Author: Adams, Ryan Prescott; Snoek, Jasper; Larochelle, Hugo

Note: Order does not necessarily reflect citation order of authors.

Citation: Snoek, Jasper, Ryan P. Adams, and Hugo Larochelle. 2012. On nonparametric guidance for learning autoencoder representations. In Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics: April 21-23, 2012 La Palma, Canary Islands, ed. Neil Lawrence and Mark Girolami, JMLR Workshop and Conference Proceedings 22:1073-1080.
Full Text & Related Files:
Abstract: Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for learning features relevant to discriminative tasks. Autoencoders, in particular, have proven to be an effective way to learn latent codes that reflect meaningful variations in data. A continuing challenge, however, is guiding an autoencoder toward representations that are useful for particular tasks. A complementary challenge is to find codes that are invariant to irrelevant transformations of the data. The most common way of introducing such problem-specific guidance in autoencoders has been through the incorporation of a parametric component that ties the latent representation to the label information. In this work, we argue that a preferable approach relies instead on a nonparametric guidance mechanism. Conceptually, it ensures that there exists a function that can predict the label information, without explicitly instantiating that function. The superiority of this guidance mechanism is con- firmed on two datasets. In particular, this approach is able to incorporate invariance information (lighting, elevation, etc.) from the small NORB object recognition dataset and yields state-of-the-art performance for a single layer, non-convolutional network.
Published Version: http://jmlr.csail.mit.edu/proceedings/papers/v22/snoek12/snoek12.pdf
Terms of Use: This article is made available under the terms and conditions applicable to Open Access Policy Articles, as set forth at http://nrs.harvard.edu/urn-3:HUL.InstRepos:dash.current.terms-of-use#OAP
Citable link to this page: http://nrs.harvard.edu/urn-3:HUL.InstRepos:8712190
Downloads of this work:

Show full Dublin Core record

This item appears in the following Collection(s)


Search DASH

Advanced Search