Back to Search
Start Over
Why concepts are (probably) vectors.
- Source :
-
Trends in cognitive sciences [Trends Cogn Sci] 2024 Aug 06. Date of Electronic Publication: 2024 Aug 06. - Publication Year :
- 2024
- Publisher :
- Ahead of Print
-
Abstract
- For decades, cognitive scientists have debated what kind of representation might characterize human concepts. Whatever the format of the representation, it must allow for the computation of varied properties, including similarities, features, categories, definitions, and relations. It must also support the development of theories, ad hoc categories, and knowledge of procedures. Here, we discuss why vector-based representations provide a compelling account that can meet all these needs while being plausibly encoded into neural architectures. This view has become especially promising with recent advances in both large language models and vector symbolic architectures. These innovations show how vectors can handle many properties traditionally thought to be out of reach for neural models, including compositionality, definitions, structures, and symbolic computational processes.<br />Competing Interests: Declaration of interests No interests are declared.<br /> (Copyright © 2024. Published by Elsevier Ltd.)
Details
- Language :
- English
- ISSN :
- 1879-307X
- Database :
- MEDLINE
- Journal :
- Trends in cognitive sciences
- Publication Type :
- Academic Journal
- Accession number :
- 39112125
- Full Text :
- https://doi.org/10.1016/j.tics.2024.06.011