An Information-Theoretic Approach to Cognitive Dimension Reduction

Abstract

We introduce Cognitive Dimension Reduction (CDR), a model that sheds light on how individuals simplify the multidimensional world to guide decision-making and comprehension. Our proposal posits that cognitive limitations prompt the adoption of simplified models, reducing the environment to a subset of dimensions. Within these limitations, we propose that individuals exploit both environment structure and goal relevance. Employing Information Theory, we formalize these principles and develop a model that explains how environmental and cognitive factors influence dimension reduction. Furthermore, we present an experimental method for CDR assessment and initial findings that support it.

Cite

Text

Leshkowitz. "An Information-Theoretic Approach to Cognitive Dimension Reduction." NeurIPS 2023 Workshops: InfoCog, 2023.

Markdown

[Leshkowitz. "An Information-Theoretic Approach to Cognitive Dimension Reduction." NeurIPS 2023 Workshops: InfoCog, 2023.](https://mlanthology.org/neuripsw/2023/leshkowitz2023neuripsw-informationtheoretic/)

BibTeX

@inproceedings{leshkowitz2023neuripsw-informationtheoretic,
  title     = {{An Information-Theoretic Approach to Cognitive Dimension Reduction}},
  author    = {Leshkowitz, Maya},
  booktitle = {NeurIPS 2023 Workshops: InfoCog},
  year      = {2023},
  url       = {https://mlanthology.org/neuripsw/2023/leshkowitz2023neuripsw-informationtheoretic/}
}