Application of neural network to humanoid robots - Development of co-associative memory model

Kazuko Itoh, Hiroyasu Miwa, Hideaki Takanobu, Atsuo Takanishi

    Research output: Contribution to journalArticle

    5 Citations (Scopus)

    Abstract

    We have been studying a system of many harmonic oscillators (neurons) interacting via a chaotic force since 2002. Each harmonic oscillator is driven by chaotic force whose bifurcation parameter is modulated by the position of the harmonic oscillator. Moreover, a system of mutually coupled chaotic neural networks was investigated. Different patterns were stored in each network and the associative memory problem was discussed in these networks. Each network can retrieve the pattern stored in the other network. On the other hand, we have been developing new mechanisms and functions for a humanoid robot with the ability to express emotions and communicate with humans in a human-like manner. We introduced a mental model which consisted of the mental space, the mood, the equations of emotion, the robot personality, the need model, the consciousness model and the behavior model. This type of mental model was implemented in Emotion Expression Humanoid Robot WE-4RII (Waseda Eye No.4 Refined II). In this paper, an associative memory model using mutually coupled chaotic neural networks is proposed for retrieving optimum memory (recognition) in response to a stimulus. We implemented this model in Emotion Expression Humanoid Robot WE-4RII (Waseda Eye No.4 Refined II).

    Original languageEnglish
    Pages (from-to)666-673
    Number of pages8
    JournalNeural Networks
    Volume18
    Issue number5-6
    DOIs
    Publication statusPublished - 2005 Jul

    Fingerprint

    Emotions
    Robots
    Neural networks
    Data storage equipment
    Aptitude
    Consciousness
    Personality
    Neurons

    Keywords

    • Associative memory
    • Humanoid robot
    • Neural network

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Neuroscience(all)

    Cite this

    Application of neural network to humanoid robots - Development of co-associative memory model. / Itoh, Kazuko; Miwa, Hiroyasu; Takanobu, Hideaki; Takanishi, Atsuo.

    In: Neural Networks, Vol. 18, No. 5-6, 07.2005, p. 666-673.

    Research output: Contribution to journalArticle

    Itoh, Kazuko ; Miwa, Hiroyasu ; Takanobu, Hideaki ; Takanishi, Atsuo. / Application of neural network to humanoid robots - Development of co-associative memory model. In: Neural Networks. 2005 ; Vol. 18, No. 5-6. pp. 666-673.
    @article{60f5c6ceba034c0582c100f13efd6635,
    title = "Application of neural network to humanoid robots - Development of co-associative memory model",
    abstract = "We have been studying a system of many harmonic oscillators (neurons) interacting via a chaotic force since 2002. Each harmonic oscillator is driven by chaotic force whose bifurcation parameter is modulated by the position of the harmonic oscillator. Moreover, a system of mutually coupled chaotic neural networks was investigated. Different patterns were stored in each network and the associative memory problem was discussed in these networks. Each network can retrieve the pattern stored in the other network. On the other hand, we have been developing new mechanisms and functions for a humanoid robot with the ability to express emotions and communicate with humans in a human-like manner. We introduced a mental model which consisted of the mental space, the mood, the equations of emotion, the robot personality, the need model, the consciousness model and the behavior model. This type of mental model was implemented in Emotion Expression Humanoid Robot WE-4RII (Waseda Eye No.4 Refined II). In this paper, an associative memory model using mutually coupled chaotic neural networks is proposed for retrieving optimum memory (recognition) in response to a stimulus. We implemented this model in Emotion Expression Humanoid Robot WE-4RII (Waseda Eye No.4 Refined II).",
    keywords = "Associative memory, Humanoid robot, Neural network",
    author = "Kazuko Itoh and Hiroyasu Miwa and Hideaki Takanobu and Atsuo Takanishi",
    year = "2005",
    month = "7",
    doi = "10.1016/j.neunet.2005.06.021",
    language = "English",
    volume = "18",
    pages = "666--673",
    journal = "Neural Networks",
    issn = "0893-6080",
    publisher = "Elsevier Limited",
    number = "5-6",

    }

    TY - JOUR

    T1 - Application of neural network to humanoid robots - Development of co-associative memory model

    AU - Itoh, Kazuko

    AU - Miwa, Hiroyasu

    AU - Takanobu, Hideaki

    AU - Takanishi, Atsuo

    PY - 2005/7

    Y1 - 2005/7

    N2 - We have been studying a system of many harmonic oscillators (neurons) interacting via a chaotic force since 2002. Each harmonic oscillator is driven by chaotic force whose bifurcation parameter is modulated by the position of the harmonic oscillator. Moreover, a system of mutually coupled chaotic neural networks was investigated. Different patterns were stored in each network and the associative memory problem was discussed in these networks. Each network can retrieve the pattern stored in the other network. On the other hand, we have been developing new mechanisms and functions for a humanoid robot with the ability to express emotions and communicate with humans in a human-like manner. We introduced a mental model which consisted of the mental space, the mood, the equations of emotion, the robot personality, the need model, the consciousness model and the behavior model. This type of mental model was implemented in Emotion Expression Humanoid Robot WE-4RII (Waseda Eye No.4 Refined II). In this paper, an associative memory model using mutually coupled chaotic neural networks is proposed for retrieving optimum memory (recognition) in response to a stimulus. We implemented this model in Emotion Expression Humanoid Robot WE-4RII (Waseda Eye No.4 Refined II).

    AB - We have been studying a system of many harmonic oscillators (neurons) interacting via a chaotic force since 2002. Each harmonic oscillator is driven by chaotic force whose bifurcation parameter is modulated by the position of the harmonic oscillator. Moreover, a system of mutually coupled chaotic neural networks was investigated. Different patterns were stored in each network and the associative memory problem was discussed in these networks. Each network can retrieve the pattern stored in the other network. On the other hand, we have been developing new mechanisms and functions for a humanoid robot with the ability to express emotions and communicate with humans in a human-like manner. We introduced a mental model which consisted of the mental space, the mood, the equations of emotion, the robot personality, the need model, the consciousness model and the behavior model. This type of mental model was implemented in Emotion Expression Humanoid Robot WE-4RII (Waseda Eye No.4 Refined II). In this paper, an associative memory model using mutually coupled chaotic neural networks is proposed for retrieving optimum memory (recognition) in response to a stimulus. We implemented this model in Emotion Expression Humanoid Robot WE-4RII (Waseda Eye No.4 Refined II).

    KW - Associative memory

    KW - Humanoid robot

    KW - Neural network

    UR - http://www.scopus.com/inward/record.url?scp=27744472101&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=27744472101&partnerID=8YFLogxK

    U2 - 10.1016/j.neunet.2005.06.021

    DO - 10.1016/j.neunet.2005.06.021

    M3 - Article

    VL - 18

    SP - 666

    EP - 673

    JO - Neural Networks

    JF - Neural Networks

    SN - 0893-6080

    IS - 5-6

    ER -