Neural Models for Part-Whole Hierarchies
Abstract
We present a connectionist method for representing images that ex(cid:173) plicitly addresses their hierarchical nature. It blends data from neu(cid:173) roscience about whole-object viewpoint sensitive cells in inferotem(cid:173) poral cortex8 and attentional basis-field modulation in V43 with ideas about hierarchical descriptions based on microfeatures.5,11 The resulting model makes critical use of bottom-up and top-down pathways for analysis and synthesis.6 We illustrate the model with a simple example of representing information about faces.
Cite
Text
Riesenhuber and Dayan. "Neural Models for Part-Whole Hierarchies." Neural Information Processing Systems, 1996.Markdown
[Riesenhuber and Dayan. "Neural Models for Part-Whole Hierarchies." Neural Information Processing Systems, 1996.](https://mlanthology.org/neurips/1996/riesenhuber1996neurips-neural/)BibTeX
@inproceedings{riesenhuber1996neurips-neural,
title = {{Neural Models for Part-Whole Hierarchies}},
author = {Riesenhuber, Maximilian and Dayan, Peter},
booktitle = {Neural Information Processing Systems},
year = {1996},
pages = {17-26},
url = {https://mlanthology.org/neurips/1996/riesenhuber1996neurips-neural/}
}