Cargando…

SERKET: An Architecture for Connecting Stochastic Models to Realize a Large-Scale Cognitive Model

To realize human-like robot intelligence, a large-scale cognitive architecture is required for robots to understand their environment through a variety of sensors with which they are equipped. In this paper, we propose a novel framework named Serket that enables the construction of a large-scale gen...

Descripción completa

Detalles Bibliográficos
Autores principales: Nakamura, Tomoaki, Nagai, Takayuki, Taniguchi, Tadahiro
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6028621/
https://www.ncbi.nlm.nih.gov/pubmed/29997493
http://dx.doi.org/10.3389/fnbot.2018.00025
_version_ 1783336804244520960
author Nakamura, Tomoaki
Nagai, Takayuki
Taniguchi, Tadahiro
author_facet Nakamura, Tomoaki
Nagai, Takayuki
Taniguchi, Tadahiro
author_sort Nakamura, Tomoaki
collection PubMed
description To realize human-like robot intelligence, a large-scale cognitive architecture is required for robots to understand their environment through a variety of sensors with which they are equipped. In this paper, we propose a novel framework named Serket that enables the construction of a large-scale generative model and its inferences easily by connecting sub-modules to allow the robots to acquire various capabilities through interaction with their environment and others. We consider that large-scale cognitive models can be constructed by connecting smaller fundamental models hierarchically while maintaining their programmatic independence. Moreover, the connected modules are dependent on each other and their parameters must be optimized as a whole. Conventionally, the equations for parameter estimation have to be derived and implemented depending on the models. However, it has become harder to derive and implement equations of large-scale models. Thus, in this paper, we propose a parameter estimation method that communicates the minimum parameters between various modules while maintaining their programmatic independence. Therefore, Serket makes it easy to construct large-scale models and estimate their parameters via the connection of modules. Experimental results demonstrated that the model can be constructed by connecting modules, the parameters can be optimized as a whole, and they are comparable with the original models that we have proposed.
format Online
Article
Text
id pubmed-6028621
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-60286212018-07-11 SERKET: An Architecture for Connecting Stochastic Models to Realize a Large-Scale Cognitive Model Nakamura, Tomoaki Nagai, Takayuki Taniguchi, Tadahiro Front Neurorobot Neuroscience To realize human-like robot intelligence, a large-scale cognitive architecture is required for robots to understand their environment through a variety of sensors with which they are equipped. In this paper, we propose a novel framework named Serket that enables the construction of a large-scale generative model and its inferences easily by connecting sub-modules to allow the robots to acquire various capabilities through interaction with their environment and others. We consider that large-scale cognitive models can be constructed by connecting smaller fundamental models hierarchically while maintaining their programmatic independence. Moreover, the connected modules are dependent on each other and their parameters must be optimized as a whole. Conventionally, the equations for parameter estimation have to be derived and implemented depending on the models. However, it has become harder to derive and implement equations of large-scale models. Thus, in this paper, we propose a parameter estimation method that communicates the minimum parameters between various modules while maintaining their programmatic independence. Therefore, Serket makes it easy to construct large-scale models and estimate their parameters via the connection of modules. Experimental results demonstrated that the model can be constructed by connecting modules, the parameters can be optimized as a whole, and they are comparable with the original models that we have proposed. Frontiers Media S.A. 2018-06-26 /pmc/articles/PMC6028621/ /pubmed/29997493 http://dx.doi.org/10.3389/fnbot.2018.00025 Text en Copyright © 2018 Nakamura, Nagai and Taniguchi. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Nakamura, Tomoaki
Nagai, Takayuki
Taniguchi, Tadahiro
SERKET: An Architecture for Connecting Stochastic Models to Realize a Large-Scale Cognitive Model
title SERKET: An Architecture for Connecting Stochastic Models to Realize a Large-Scale Cognitive Model
title_full SERKET: An Architecture for Connecting Stochastic Models to Realize a Large-Scale Cognitive Model
title_fullStr SERKET: An Architecture for Connecting Stochastic Models to Realize a Large-Scale Cognitive Model
title_full_unstemmed SERKET: An Architecture for Connecting Stochastic Models to Realize a Large-Scale Cognitive Model
title_short SERKET: An Architecture for Connecting Stochastic Models to Realize a Large-Scale Cognitive Model
title_sort serket: an architecture for connecting stochastic models to realize a large-scale cognitive model
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6028621/
https://www.ncbi.nlm.nih.gov/pubmed/29997493
http://dx.doi.org/10.3389/fnbot.2018.00025
work_keys_str_mv AT nakamuratomoaki serketanarchitectureforconnectingstochasticmodelstorealizealargescalecognitivemodel
AT nagaitakayuki serketanarchitectureforconnectingstochasticmodelstorealizealargescalecognitivemodel
AT taniguchitadahiro serketanarchitectureforconnectingstochasticmodelstorealizealargescalecognitivemodel