Similarity, Connectionism, and the Problem of Representation in Vision

Abstract

A representational scheme under which the ranking between represented similarities is isomorphic to the ranking between the corresponding shape similarities can support perfectly correct shape classification because it preserves the clustering of shapes according to the natural kinds prevailing in the external world. This article discusses the computational requirements of representation that preserves similarity ranks and points out the relative straightforwardness of its connectionist implementation.

Cite

Text

Edelman and Duvdevani-Bar. "Similarity, Connectionism, and the Problem of Representation in Vision." Neural Computation, 1997. doi:10.1162/NECO.1997.9.4.701

Markdown

[Edelman and Duvdevani-Bar. "Similarity, Connectionism, and the Problem of Representation in Vision." Neural Computation, 1997.](https://mlanthology.org/neco/1997/edelman1997neco-similarity/) doi:10.1162/NECO.1997.9.4.701

BibTeX

@article{edelman1997neco-similarity,
  title     = {{Similarity, Connectionism, and the Problem of Representation in Vision}},
  author    = {Edelman, Shimon and Duvdevani-Bar, Sharon},
  journal   = {Neural Computation},
  year      = {1997},
  pages     = {701-721},
  doi       = {10.1162/NECO.1997.9.4.701},
  volume    = {9},
  url       = {https://mlanthology.org/neco/1997/edelman1997neco-similarity/}
}