Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus BASE kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

Intertwining Generalization and Memorization

Title: Intertwining Generalization and Memorization
Authors: Coxe-Conklin, Henry; Smith, Kenny
Source: Proceedings of the Annual Meeting of the Cognitive Science Society, vol 44, iss 44
Publisher Information: eScholarship, University of California
Publication Year: 2022
Collection: University of California: eScholarship
Subject Terms: Artificial Intelligence; Computer Science; Linguistics; Complex systems; Evolution; Natural Language Processing; Syntax; Agent-based Modeling; Neural Networks
Description: Over-paramaterized neural models have become dominant in Natural Language Processing. Increasing the size of a neural network seems to result in improved performance across a a broad range of tasks. Despite their size these models have been shown to generalize poorly outside their training data. Seemingly failing to extract the systematic generalizations that humans use to generate and interpret language. Increasingly work has questioned whether these models are learning to generalize or memorize, with larger capacity models potentially just memorizing their data more and more effectively. We suggest the tradeoff between memorization and generalization may be more nuanced; with the capacity of a model shaping the kinds of generalizations they are likely to acquire. Our results on a linguistic task suggest that while all models develop generalization strategies, smaller models may arrive at a smaller distribution of strategies that generalize more robustly to novel data.
Document Type: article in journal/newspaper
File Description: application/pdf
Language: unknown
Relation: qt5032871c; https://escholarship.org/uc/item/5032871c; https://escholarship.org/content/qt5032871c/qt5032871c.pdf
Availability: https://escholarship.org/uc/item/5032871c; https://escholarship.org/content/qt5032871c/qt5032871c.pdf
Rights: CC-BY
Accession Number: edsbas.18EA1446
Database: BASE