A Productive, Systematic Framework for the Representation of Visual Structure
Abstract
We describe a unified framework for the understanding of struc(cid:173) ture representation in primate vision. A model derived from this framework is shown to be effectively systematic in that it has the ability to interpret and associate together objects that are related through a rearrangement of common "middle-scale" parts, repre(cid:173) sented as image fragments. The model addresses the same concerns as previous work on compositional representation through the use of what+where receptive fields and attentional gain modulation. It does not require prior exposure to the individual parts, and avoids the need for abstract symbolic binding.
Cite
Text
Edelman and Intrator. "A Productive, Systematic Framework for the Representation of Visual Structure." Neural Information Processing Systems, 2000.Markdown
[Edelman and Intrator. "A Productive, Systematic Framework for the Representation of Visual Structure." Neural Information Processing Systems, 2000.](https://mlanthology.org/neurips/2000/edelman2000neurips-productive/)BibTeX
@inproceedings{edelman2000neurips-productive,
title = {{A Productive, Systematic Framework for the Representation of Visual Structure}},
author = {Edelman, Shimon and Intrator, Nathan},
booktitle = {Neural Information Processing Systems},
year = {2000},
pages = {10-16},
url = {https://mlanthology.org/neurips/2000/edelman2000neurips-productive/}
}