Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes

Abstract

We show how to use unlabeled data and a deep belief net (DBN) to learn a good covariance kernel for a Gaussian process. We first learn a deep generative model of the unlabeled data using the fast, greedy algorithm introduced by Hinton et.al. If the data is high-dimensional and highly-structured, a Gaussian kernel applied to the top layer of features in the DBN works much better than a similar kernel applied to the raw input. Performance at both regression and classification can then be further improved by using backpropagation through the DBN to discriminatively fine-tune the covariance kernel.

Cite

Text

Hinton and Salakhutdinov. "Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes." Neural Information Processing Systems, 2007.

Markdown

[Hinton and Salakhutdinov. "Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes." Neural Information Processing Systems, 2007.](https://mlanthology.org/neurips/2007/hinton2007neurips-using/)

BibTeX

@inproceedings{hinton2007neurips-using,
  title     = {{Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes}},
  author    = {Hinton, Geoffrey E. and Salakhutdinov, Ruslan},
  booktitle = {Neural Information Processing Systems},
  year      = {2007},
  pages     = {1249-1256},
  url       = {https://mlanthology.org/neurips/2007/hinton2007neurips-using/}
}