Learning the Structure of Similarity
Abstract
The additive clustering (ADCL US) model (Shepard & Arabie, 1979) treats the similarity of two stimuli as a weighted additive measure of their common features. Inspired by recent work in unsupervised learning with multiple cause models, we propose anew, statistically well-motivated algorithm for discovering the structure of natural stimulus classes using the ADCLUS model, which promises substan(cid:173) tial gains in conceptual simplicity, practical efficiency, and solution quality over earlier efforts. We also present preliminary results with artificial data and two classic similarity data sets.
Cite
Text
Tenenbaum. "Learning the Structure of Similarity." Neural Information Processing Systems, 1995.Markdown
[Tenenbaum. "Learning the Structure of Similarity." Neural Information Processing Systems, 1995.](https://mlanthology.org/neurips/1995/tenenbaum1995neurips-learning/)BibTeX
@inproceedings{tenenbaum1995neurips-learning,
title = {{Learning the Structure of Similarity}},
author = {Tenenbaum, Joshua B.},
booktitle = {Neural Information Processing Systems},
year = {1995},
pages = {3-9},
url = {https://mlanthology.org/neurips/1995/tenenbaum1995neurips-learning/}
}