License: 
Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/DagSemProc.08041.6
URN: urn:nbn:de:0030-drops-14213
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2008/1421/
|
Go to the corresponding Portal |
Van der Velde, Frank ;
de Kamps, Marc
The role of recurrent networks in neural architectures of grounded cognition: learning of control
Abstract
Recurrent networks have been used as neural models of language processing, with mixed results. Here, we discuss the role of recurrent networks in a neural architecture of grounded cognition. In particular, we discuss how the control of binding in this architecture can be learned. We trained a simple recurrent network (SRN) and a feedforward network (FFN) for this task. The results show that information from the architecture is needed as input for these networks to learn control of binding. Thus, both control systems are recurrent. We found that the recurrent system consisting of the architecture and an SRN or an FFN as a "core" can learn basic (but recursive) sentence structures. Problems with control of binding arise when the system with the SRN is tested on number of new sentence structures. In contrast, control of binding for these structures succeeds with the FFN. Yet, for some structures with (unlimited) embeddings, difficulties arise due to dynamical binding conflicts in the architecture itself. In closing, we discuss potential future developments of the architecture presented here.
BibTeX - Entry
@InProceedings{vandervelde_et_al:DagSemProc.08041.6,
author = {Van der Velde, Frank and de Kamps, Marc},
title = {{The role of recurrent networks in neural architectures of grounded cognition: learning of control}},
booktitle = {Recurrent Neural Networks- Models, Capacities, and Applications},
pages = {1--18},
series = {Dagstuhl Seminar Proceedings (DagSemProc)},
ISSN = {1862-4405},
year = {2008},
volume = {8041},
editor = {Luc De Raedt and Barbara Hammer and Pascal Hitzler and Wolfgang Maass},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/opus/volltexte/2008/1421},
URN = {urn:nbn:de:0030-drops-14213},
doi = {10.4230/DagSemProc.08041.6},
annote = {Keywords: Grounded representations, binding control, combinatorial structures, neural architecture, recurrent network, learning}
}
|
Keywords: |
|
Grounded representations, binding control, combinatorial structures, neural architecture, recurrent network, learning |
|
Collection: |
|
08041 - Recurrent Neural Networks- Models, Capacities, and Applications |
|
Issue Date: |
|
2008 |
|
Date of publication: |
|
15.04.2008 |
