Integration of behaviors and languages with a hierarchal structure self-organized in a neuro-dynamical model

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    9 Citations (Scopus)

    Abstract

    This paper proposes an approach for robots to ac-quire language grounding in their robot's sensory-motor flow using neuro-dynamical models. We trained our neuro-dynamical model over a set of sentences represented as sequences of characters. For the integrated recognition, we introduced a cognitive hypothesis for integrated recognition where a human's brain separately processed the 'structure' and 'contents' of a sentence. Our model was trained with the spelling of words and their semantic role emerged in the first model. As a result of binding the model with sensory-motion patterns, we confirmed that it could associate proper word spellings with a sensory-motor flows and a semantic roles, even if an observed flow had not been learned.

    Original languageEnglish
    Title of host publicationProceedings of the 2013 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
    Pages89-95
    Number of pages7
    DOIs
    Publication statusPublished - 2013
    Event2013 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 - Singapore
    Duration: 2013 Apr 162013 Apr 19

    Other

    Other2013 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
    CitySingapore
    Period13/4/1613/4/19

    Fingerprint

    Semantics
    Robots
    Electric grounding
    Brain

    Keywords

    • behaviors
    • language grammer
    • neuro-dynamical systems
    • symbol grounding
    • word contents

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Human-Computer Interaction

    Cite this

    Ogata, T., & Okuno, H. G. (2013). Integration of behaviors and languages with a hierarchal structure self-organized in a neuro-dynamical model. In Proceedings of the 2013 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 (pp. 89-95). [6607934] https://doi.org/10.1109/RiiSS.2013.6607934

    Integration of behaviors and languages with a hierarchal structure self-organized in a neuro-dynamical model. / Ogata, Tetsuya; Okuno, Hiroshi G.

    Proceedings of the 2013 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. p. 89-95 6607934.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Ogata, T & Okuno, HG 2013, Integration of behaviors and languages with a hierarchal structure self-organized in a neuro-dynamical model. in Proceedings of the 2013 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013., 6607934, pp. 89-95, 2013 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013, Singapore, 13/4/16. https://doi.org/10.1109/RiiSS.2013.6607934
    Ogata T, Okuno HG. Integration of behaviors and languages with a hierarchal structure self-organized in a neuro-dynamical model. In Proceedings of the 2013 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. p. 89-95. 6607934 https://doi.org/10.1109/RiiSS.2013.6607934
    Ogata, Tetsuya ; Okuno, Hiroshi G. / Integration of behaviors and languages with a hierarchal structure self-organized in a neuro-dynamical model. Proceedings of the 2013 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. pp. 89-95
    @inproceedings{2f425e64e59c43199333b9f9645d20ec,
    title = "Integration of behaviors and languages with a hierarchal structure self-organized in a neuro-dynamical model",
    abstract = "This paper proposes an approach for robots to ac-quire language grounding in their robot's sensory-motor flow using neuro-dynamical models. We trained our neuro-dynamical model over a set of sentences represented as sequences of characters. For the integrated recognition, we introduced a cognitive hypothesis for integrated recognition where a human's brain separately processed the 'structure' and 'contents' of a sentence. Our model was trained with the spelling of words and their semantic role emerged in the first model. As a result of binding the model with sensory-motion patterns, we confirmed that it could associate proper word spellings with a sensory-motor flows and a semantic roles, even if an observed flow had not been learned.",
    keywords = "behaviors, language grammer, neuro-dynamical systems, symbol grounding, word contents",
    author = "Tetsuya Ogata and Okuno, {Hiroshi G.}",
    year = "2013",
    doi = "10.1109/RiiSS.2013.6607934",
    language = "English",
    isbn = "9781467358774",
    pages = "89--95",
    booktitle = "Proceedings of the 2013 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013",

    }

    TY - GEN

    T1 - Integration of behaviors and languages with a hierarchal structure self-organized in a neuro-dynamical model

    AU - Ogata, Tetsuya

    AU - Okuno, Hiroshi G.

    PY - 2013

    Y1 - 2013

    N2 - This paper proposes an approach for robots to ac-quire language grounding in their robot's sensory-motor flow using neuro-dynamical models. We trained our neuro-dynamical model over a set of sentences represented as sequences of characters. For the integrated recognition, we introduced a cognitive hypothesis for integrated recognition where a human's brain separately processed the 'structure' and 'contents' of a sentence. Our model was trained with the spelling of words and their semantic role emerged in the first model. As a result of binding the model with sensory-motion patterns, we confirmed that it could associate proper word spellings with a sensory-motor flows and a semantic roles, even if an observed flow had not been learned.

    AB - This paper proposes an approach for robots to ac-quire language grounding in their robot's sensory-motor flow using neuro-dynamical models. We trained our neuro-dynamical model over a set of sentences represented as sequences of characters. For the integrated recognition, we introduced a cognitive hypothesis for integrated recognition where a human's brain separately processed the 'structure' and 'contents' of a sentence. Our model was trained with the spelling of words and their semantic role emerged in the first model. As a result of binding the model with sensory-motion patterns, we confirmed that it could associate proper word spellings with a sensory-motor flows and a semantic roles, even if an observed flow had not been learned.

    KW - behaviors

    KW - language grammer

    KW - neuro-dynamical systems

    KW - symbol grounding

    KW - word contents

    UR - http://www.scopus.com/inward/record.url?scp=84886570523&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84886570523&partnerID=8YFLogxK

    U2 - 10.1109/RiiSS.2013.6607934

    DO - 10.1109/RiiSS.2013.6607934

    M3 - Conference contribution

    AN - SCOPUS:84886570523

    SN - 9781467358774

    SP - 89

    EP - 95

    BT - Proceedings of the 2013 IEEE Workshop on Robotic Intelligence in Informationally Structured Space, RiiSS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

    ER -