@inproceedings{b8cc84f992f141a0bc5e03a10e8ca6a5,
title = "Compression: A lossless mechanism for learning complex structured relational representations",
abstract = "People learn by both decomposing and combining concepts; most accounts of combination are either compositional or conjunctive. We augment the DORA model of representation learning to build new predicate representation by combining (or compressing) existing predicate representations (e.g., building a predicate a_b by combining predicates a and b). The resulting model learns structured relational representations from experience and then combines these relational concepts to form more complex, compressed concepts. We show that the resulting model provides an account of a category learning experiment in which categories are defined as novel combinations of relational concepts.",
keywords = "chunking, comparison, compression, computational modeling, mapping, relational categorisation, symbolic-connectionist model",
author = "Ekaterina Shurkova and Doumas, {Leonidas A.A.}",
year = "2021",
month = jul,
day = "29",
language = "English",
volume = "43",
series = "Proceedings of the Annual Meeting of the Cognitive Science Society",
publisher = "The Cognitive Science Society",
pages = "293--299",
editor = "Tecumseh Fitch and Claus Lamm and Helmut Leder and Kristin Te{\ss}mar-Raible",
booktitle = "Proceedings of the 43rd Annual Meeting of the Cognitive Science Society",
note = "43rd Annual Meeting of the Cognitive Science Society: Comparative Cognition: Animal Minds, CogSci 2021 ; Conference date: 26-07-2021 Through 29-07-2021",
}