A connectionist model of reading with error correction properties - Ecole Nationale d'Ingénieurs de Brest Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

A connectionist model of reading with error correction properties

Résumé

Recent models of associative long term memory (LTM) have emerged in the field of neuro-inspired computing. These models have interesting properties of error correction, robustness, storage capacity and retrieval performance. In this context, we propose a connectionist model of written word recognition with correction properties, using associative memories based on neural cliques. Similarly to what occurs in human language, the model takes advantage of the combination of phonological and orthographic information to increase the retrieval performance in error cases. Therefore, the proposed architecture and principles of this work could be applied to other neuro-inspired problems that involve multimodal processing, in particular for language applications.
Fichier non déposé

Dates et versions

hal-01311631 , version 1 (04-05-2016)

Identifiants

  • HAL Id : hal-01311631 , version 1

Citer

Max Raphael Sobroza Marques, Xiaoran Jiang, Olivier Dufor, Claude Berrou, Deok-Hee Kim-Dufor. A connectionist model of reading with error correction properties. LTC 2015 : 7th Language and Technology Conference, Nov 2015, Poznan, Poland. pp.455 - 460. ⟨hal-01311631⟩
238 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More