On Nonparametric Guidance for Learning Autoencoder Representations

Details On Nonparametric Guidance for Learning Autoencoder Representations On Nonparametric Guidance for Learning Autoencoder Representations

2011-02-08

arxiv.org/abs/1102.1492v4

Statistics

Machine Learning

9 pages, 12 figures

Scientific paper

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 confirmed 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.

Affiliated with

Also associated with

No associations

Rating

On Nonparametric Guidance for Learning Autoencoder Representations does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with On Nonparametric Guidance for Learning Autoencoder Representations, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and On Nonparametric Guidance for Learning Autoencoder Representations will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-501923