On the Emergence of Novel Behaviours From Complex Non Linear Systems

Lorenzo Riano, TM McGinnity

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

    Abstract

    Emergent behaviours are believed to be a property of complex cognitive architectures. However it is difficult to observe them in carefully engineered systems. We believe that, in order to obtain interesting and surprising behaviours, the designer has to remove some predictability requirements. To explore this we studied how the complexity, defined according to the Kolmogorov theory, is linked to truly emergent behaviours. This study has been conducted on a real robot driven by the non-linear dynamics of a recurrent neural network created using evolutionary approaches. In several experiments we found that, while a simple network is equivalent to a deterministic automata, networks of increasing complexity exhibit novel behaviours. This is due to a spontaneous background activity of the neurons which can be sustained only by a complex network. These results support the idea that in a non predictable architecture novel and surprising cognitive capabilities emerge in a natural way.
    LanguageEnglish
    Title of host publicationUnknown Host Publication
    PublisherIOS Press
    Number of pages10
    Publication statusPublished - 2010
    EventProceeding of BICA 2010, International Conference on Biological Inspired Cognitive Architectures -
    Duration: 1 Jan 2010 → …

    Conference

    ConferenceProceeding of BICA 2010, International Conference on Biological Inspired Cognitive Architectures
    Period1/01/10 → …

    Fingerprint

    Recurrent neural networks
    Complex networks
    Neurons
    Nonlinear systems
    Robots
    Experiments

    Keywords

    • cognitive robotics
    • genetic algorithms
    • neural networks
    • non linear

    Cite this

    Riano, L., & McGinnity, TM. (2010). On the Emergence of Novel Behaviours From Complex Non Linear Systems. In Unknown Host Publication IOS Press.
    Riano, Lorenzo ; McGinnity, TM. / On the Emergence of Novel Behaviours From Complex Non Linear Systems. Unknown Host Publication. IOS Press, 2010.
    @inproceedings{296be5a551584099a2f631ed27d4269d,
    title = "On the Emergence of Novel Behaviours From Complex Non Linear Systems",
    abstract = "Emergent behaviours are believed to be a property of complex cognitive architectures. However it is difficult to observe them in carefully engineered systems. We believe that, in order to obtain interesting and surprising behaviours, the designer has to remove some predictability requirements. To explore this we studied how the complexity, defined according to the Kolmogorov theory, is linked to truly emergent behaviours. This study has been conducted on a real robot driven by the non-linear dynamics of a recurrent neural network created using evolutionary approaches. In several experiments we found that, while a simple network is equivalent to a deterministic automata, networks of increasing complexity exhibit novel behaviours. This is due to a spontaneous background activity of the neurons which can be sustained only by a complex network. These results support the idea that in a non predictable architecture novel and surprising cognitive capabilities emerge in a natural way.",
    keywords = "cognitive robotics, genetic algorithms, neural networks, non linear",
    author = "Lorenzo Riano and TM McGinnity",
    year = "2010",
    language = "English",
    booktitle = "Unknown Host Publication",
    publisher = "IOS Press",
    address = "Netherlands",

    }

    Riano, L & McGinnity, TM 2010, On the Emergence of Novel Behaviours From Complex Non Linear Systems. in Unknown Host Publication. IOS Press, Proceeding of BICA 2010, International Conference on Biological Inspired Cognitive Architectures, 1/01/10.

    On the Emergence of Novel Behaviours From Complex Non Linear Systems. / Riano, Lorenzo; McGinnity, TM.

    Unknown Host Publication. IOS Press, 2010.

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

    TY - GEN

    T1 - On the Emergence of Novel Behaviours From Complex Non Linear Systems

    AU - Riano, Lorenzo

    AU - McGinnity, TM

    PY - 2010

    Y1 - 2010

    N2 - Emergent behaviours are believed to be a property of complex cognitive architectures. However it is difficult to observe them in carefully engineered systems. We believe that, in order to obtain interesting and surprising behaviours, the designer has to remove some predictability requirements. To explore this we studied how the complexity, defined according to the Kolmogorov theory, is linked to truly emergent behaviours. This study has been conducted on a real robot driven by the non-linear dynamics of a recurrent neural network created using evolutionary approaches. In several experiments we found that, while a simple network is equivalent to a deterministic automata, networks of increasing complexity exhibit novel behaviours. This is due to a spontaneous background activity of the neurons which can be sustained only by a complex network. These results support the idea that in a non predictable architecture novel and surprising cognitive capabilities emerge in a natural way.

    AB - Emergent behaviours are believed to be a property of complex cognitive architectures. However it is difficult to observe them in carefully engineered systems. We believe that, in order to obtain interesting and surprising behaviours, the designer has to remove some predictability requirements. To explore this we studied how the complexity, defined according to the Kolmogorov theory, is linked to truly emergent behaviours. This study has been conducted on a real robot driven by the non-linear dynamics of a recurrent neural network created using evolutionary approaches. In several experiments we found that, while a simple network is equivalent to a deterministic automata, networks of increasing complexity exhibit novel behaviours. This is due to a spontaneous background activity of the neurons which can be sustained only by a complex network. These results support the idea that in a non predictable architecture novel and surprising cognitive capabilities emerge in a natural way.

    KW - cognitive robotics

    KW - genetic algorithms

    KW - neural networks

    KW - non linear

    M3 - Conference contribution

    BT - Unknown Host Publication

    PB - IOS Press

    ER -

    Riano L, McGinnity TM. On the Emergence of Novel Behaviours From Complex Non Linear Systems. In Unknown Host Publication. IOS Press. 2010