Unsupervised Grounding of Spatial Relations

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F11%3A00190987" target="_blank" >RIV/68407700:21230/11:00190987 - isvavai.cz</a>

Výsledek na webu

<a href="http://nbu.bg/cogs/eurocogsci2011/proceedings/pdfs/EuroCogSci-paper194.pdf" target="_blank" >http://nbu.bg/cogs/eurocogsci2011/proceedings/pdfs/EuroCogSci-paper194.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Unsupervised Grounding of Spatial Relations

Popis výsledku v původním jazyce

We present an unsupervised connectionist model for grounding color, shape and spatial relations of two objects in 2D space. The model constitutes a two-layer architecture that integrates information from visual and auditory inputs. The images are presented as the visual inputs to an artificial retina and five-word sentences describing them (e.g.~``Red box above green circle'') serve as auditory inputs with phonological encoding. The visual scene is represented by the Self-Organizing Map(s) and the auditory description is processed by a recursive SOM (RecSOM) that learns to topographically represent sequences. Primary representations are integrated in a multimodal module (implemented by SOM or Neural Gas algorithms) in the second layer using self-organizing units with conjunctive representations. We tested this two-layer architecture in two versions (a single SOM representing color, shape and spatial relations vs. biologically inspired separate SOMs for spatial relations and for shape a

Název v anglickém jazyce

Unsupervised Grounding of Spatial Relations

Popis výsledku anglicky

We present an unsupervised connectionist model for grounding color, shape and spatial relations of two objects in 2D space. The model constitutes a two-layer architecture that integrates information from visual and auditory inputs. The images are presented as the visual inputs to an artificial retina and five-word sentences describing them (e.g.~``Red box above green circle'') serve as auditory inputs with phonological encoding. The visual scene is represented by the Self-Organizing Map(s) and the auditory description is processed by a recursive SOM (RecSOM) that learns to topographically represent sequences. Primary representations are integrated in a multimodal module (implemented by SOM or Neural Gas algorithms) in the second layer using self-organizing units with conjunctive representations. We tested this two-layer architecture in two versions (a single SOM representing color, shape and spatial relations vs. biologically inspired separate SOMs for spatial relations and for shape a

Druh

D - Stať ve sborníku

CEP obor

AN - Psychologie

OECD FORD obor

—

Projekt

—

Návaznosti

Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

2011

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the European Conference on Cognitive Science

ISBN

978-954-535-660-5

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

443-450

Název nakladatele

New Bulgarian University

Místo vydání

Sofia

Místo konání akce

Sofia

Datum konání akce

21. 5. 2011

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—