Embodied Language Understanding with a Multiple Timescale Recurrent Neural Network

Stefan Heinrich, Cornelius Weber, Stefan Wermter

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

Abstract

How the human brain understands natural language and what we can learn for intelligent systems is open research. Recently, researchers claimed that language is embodied in most – if not all – sensory and sensorimotor modalities and that the brain’s architecture favours the emergence of language. In this paper we investigate the characteristics of such an architecture and propose a model based on the Multiple Timescale Recurrent Neural Network, extended by embodied visual perception. We show that such an architecture can learn the meaning of utterances with respect to visual perception and that it can produce verbal utterances that correctly describe previously unknown scenes.
OriginalsprogEngelsk
TitelProceedings of the 23rd International Conference on Artificial Neural Networks (ICANN2013)
RedaktørerValeri Mladenov, Petia Koprinkova-Hristova, Günther Palm, Alessandro E.P. Villa, Bruno Apolloni, Nicola Kasabov
Antal sider8
Vol/bind8131
ForlagSpringer
Publikationsdato1 sep. 2013
Sider216-223
DOI
StatusUdgivet - 1 sep. 2013
Udgivet eksterntJa
NavnLecture Notes in Computer Science

Fingeraftryk

Dyk ned i forskningsemnerne om 'Embodied Language Understanding with a Multiple Timescale Recurrent Neural Network'. Sammen danner de et unikt fingeraftryk.

Citationsformater