Learning How to Teach or Selecting Minimal Surface Data

NeurIPS 1991 pp. 364-371

/neurips/1991/geiger1991neurips-learning/

Abstract

Learning a map from an input set to an output set is similar to the prob(cid:173) lem of reconstructing hypersurfaces from sparse data (Poggio and Girosi, 1990). In this framework, we discuss the problem of automatically select(cid:173) ing "minimal" surface data. The objective is to be able to approximately reconstruct the surface from the selected sparse data. We show that this problem is equivalent to the one of compressing information by data re(cid:173) moval and the one oflearning how to teach. Our key step is to introduce a process that statistically selects the data according to the model. During the process of data selection (learning how to teach) our system (teacher) is capable of predicting the new surface, the approximated one provided by the selected data. We concentrate on piecewise smooth surfaces, e.g. images, and use mean field techniques to obtain a deterministic network that is shown to compress image data.

PDF NeurIPS Semantic Scholar

Cite

Text

Geiger and Pereira. "Learning How to Teach or Selecting Minimal Surface Data." Neural Information Processing Systems, 1991.

Markdown

[Geiger and Pereira. "Learning How to Teach or Selecting Minimal Surface Data." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/geiger1991neurips-learning/)

BibTeX

@inproceedings{geiger1991neurips-learning,
  title     = {{Learning How to Teach or Selecting Minimal Surface Data}},
  author    = {Geiger, Davi and Pereira, Ricardo A. Marques},
  booktitle = {Neural Information Processing Systems},
  year      = {1991},
  pages     = {364-371},
  url       = {https://mlanthology.org/neurips/1991/geiger1991neurips-learning/}
}