Discovering latent causes and memory modification: A computational approach using symmetry and geometry

Arif Dönmez
Proceedings of the 2nd NeurIPS Workshop on Symmetry and Geometry in Neural Representations, PMLR 228:443-458, 2024.

Abstract

We learn from our experiences, even though they are never exactly the same. This implies that we need to assess their similarity to apply what we have learned from one experience to another. It is proposed that we “cluster” our experiences based on (hidden) latent causes that we infer. It is also suggested that surprises, which occur when our predictions are incorrect, help us categorize our experiences into distinct groups. In this paper, we develop a computational theory that emulates these processes based on two basic concepts from intuitive physics and Gestalt psychology using symmetry and geometry. We apply our approach to simple tasks that involve inductive reasoning. Remarkably, the output of our computational approach aligns closely with human responses.

Cite this Paper

BibTeX
@InProceedings{pmlr-v228-donmez24a, title = {Discovering latent causes and memory modification: A computational approach using symmetry and geometry}, author = {D\"onmez, Arif}, booktitle = {Proceedings of the 2nd NeurIPS Workshop on Symmetry and Geometry in Neural Representations}, pages = {443--458}, year = {2024}, editor = {Sanborn, Sophia and Shewmake, Christian and Azeglio, Simone and Miolane, Nina}, volume = {228}, series = {Proceedings of Machine Learning Research}, month = {16 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v228/main/assets/donmez24a/donmez24a.pdf}, url = {https://proceedings.mlr.press/v228/donmez24a.html}, abstract = {We learn from our experiences, even though they are never exactly the same. This implies that we need to assess their similarity to apply what we have learned from one experience to another. It is proposed that we “cluster” our experiences based on (hidden) latent causes that we infer. It is also suggested that surprises, which occur when our predictions are incorrect, help us categorize our experiences into distinct groups. In this paper, we develop a computational theory that emulates these processes based on two basic concepts from intuitive physics and Gestalt psychology using symmetry and geometry. We apply our approach to simple tasks that involve inductive reasoning. Remarkably, the output of our computational approach aligns closely with human responses.} }
Endnote
%0 Conference Paper %T Discovering latent causes and memory modification: A computational approach using symmetry and geometry %A Arif Dönmez %B Proceedings of the 2nd NeurIPS Workshop on Symmetry and Geometry in Neural Representations %C Proceedings of Machine Learning Research %D 2024 %E Sophia Sanborn %E Christian Shewmake %E Simone Azeglio %E Nina Miolane %F pmlr-v228-donmez24a %I PMLR %P 443--458 %U https://proceedings.mlr.press/v228/donmez24a.html %V 228 %X We learn from our experiences, even though they are never exactly the same. This implies that we need to assess their similarity to apply what we have learned from one experience to another. It is proposed that we “cluster” our experiences based on (hidden) latent causes that we infer. It is also suggested that surprises, which occur when our predictions are incorrect, help us categorize our experiences into distinct groups. In this paper, we develop a computational theory that emulates these processes based on two basic concepts from intuitive physics and Gestalt psychology using symmetry and geometry. We apply our approach to simple tasks that involve inductive reasoning. Remarkably, the output of our computational approach aligns closely with human responses.
APA
Dönmez, A.. (2024). Discovering latent causes and memory modification: A computational approach using symmetry and geometry. Proceedings of the 2nd NeurIPS Workshop on Symmetry and Geometry in Neural Representations, in Proceedings of Machine Learning Research 228:443-458 Available from https://proceedings.mlr.press/v228/donmez24a.html.

Related Material