On Nonparametric Guidance for Learning Autoencoder Representations

By Jasper Snoek, Ryan P. Adams, Hugo Larochelle. 2011

20 citations recorded by the source corpus.

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 eective

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Neil D. Lawrence
2. Andreas C. Damianou
3. Huaping Liu
4. Fuchun Sun
5. Deli Zhao
6. Edward Y. Chang
7. Wen-bing Huang
8. Zoubin Ghahramani

In Computer Vision and Pattern Recognition

1. Andreas C. Damianou
2. Huaping Liu
3. Neil D. Lawrence
4. Fuchun Sun
5. Deli Zhao
6. Wen-bing Huang
7. Edward Y. Chang
8. Zoubin Ghahramani

Citations in the corpus

• Deep Gaussian Processes (2012, background): “Indeed, previous efforts to combine GPs with deep structures were successful at unsupervised pre-training [Erhan et al., 2010] or guiding [Snoek et al., 2012] of traditional deep models.”
• Scalable Gaussian Process Regression Using Deep Neural Networks (2015, methodology): “[Snoek et al., 2011] and [Damianou and Lawrence, 2012] apply GP-based building blocks as the feature extractors for highly-nonlinear regression.”