Generalization by categorical nodes in recurrent neural networks

Yoshihiko Suhara, Akito Sakurai

Research output: Contribution to journalArticle

1 Citation (Scopus)


We experimentally show that, in the grammar learning by recurrent neural networks, the networks can learn a word categorization that is consistent with the grammatical categories of words in exemplar sentences.

Original languageEnglish
Pages (from-to)161-164
Number of pages4
JournalInternational Congress Series
Publication statusPublished - 2006 Jun 1


  • Category learning
  • Grammar learning
  • Recurrent neural network

ASJC Scopus subject areas

  • Medicine(all)

Fingerprint Dive into the research topics of 'Generalization by categorical nodes in recurrent neural networks'. Together they form a unique fingerprint.

  • Cite this