Analogy-- Watershed or Waterloo? Structural Alignment and the Development of Connectionist Models of Analogy
Abstract
Neural network models have been criticized for their inability to make use of compositional representations. In this paper, we describe a series of psychological phenomena that demonstrate the role of structured representations in cognition. These findings suggest that people compare relational representations via a process of structural alignment. This process will have to be captured by any model of cognition, symbolic or subsymbolic.
Cite
Text
Gentner and Markman. "Analogy-- Watershed or Waterloo? Structural Alignment and the Development of Connectionist Models of Analogy." Neural Information Processing Systems, 1992.Markdown
[Gentner and Markman. "Analogy-- Watershed or Waterloo? Structural Alignment and the Development of Connectionist Models of Analogy." Neural Information Processing Systems, 1992.](https://mlanthology.org/neurips/1992/gentner1992neurips-analogy/)BibTeX
@inproceedings{gentner1992neurips-analogy,
title = {{Analogy-- Watershed or Waterloo? Structural Alignment and the Development of Connectionist Models of Analogy}},
author = {Gentner, Dedre and Markman, Arthur B.},
booktitle = {Neural Information Processing Systems},
year = {1992},
pages = {855-862},
url = {https://mlanthology.org/neurips/1992/gentner1992neurips-analogy/}
}