Explorer Towards a Neural Statistician

@inproceedings{Storkey2017ExplorerTA,
  title={Explorer Towards a Neural Statistician},
  author={Amos J. Storkey},
  year={2017}
}
An efficient learner is one who reuses what they already know to tackle a new problem. For a machine learner, this means understanding the similarities amongst datasets. In order to do this, one must take seriously the idea of working with datasets, rather than datapoints, as the key objects to model. Towards this goal, we demonstrate an extension of a variational autoencoder that can learn a method for computing representations, or statistics, of datasets in an unsupervised fashion. The… CONTINUE READING
0 Citations
32 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 32 references

Structured vaes: Composing probabilistic graphical models and variational autoencoders

  • Matthew J Johnson, David Duvenaud, Alexander B Wiltschko, Sandeep R Datta, Ryan P Adams
  • arXiv preprint arXiv:1603.06277,
  • 2016
1 Excerpt

Similar Papers

Loading similar papers…