Encoding Longer-term Contextual Sensorimotor Information in a Predictive Coding Model

Junpei Zhong, Tetsuya Ogata, Angelo Cangelosi

    研究成果: Conference contribution

    抄録

    Studies suggest that the difference of the sensorimotor events can be recorded with the fast- and slower-changing neural activities in the hierarchical brain areas, in which they have bi-directional connections. The slow-changing representations attempt to predict the activities on the faster level by relaying categorized sensorimotor events. On the other hand, the incoming sensory information corrects such event-based prediction on the higher level by the novel or surprising signal. From this motivation, we propose a predictive hierarchical artificial neural network model which is implemented the differentiated temporal parameters for neural updates. Also, both the fast- and slow-changing neural activities are modulated by the active motor activities. This model is examined in the driving dataset, recorded in various events, which incorporates the image sequences and the ego-motion of the vehicle. Experiments show that the model encodes the driving scenarios on the higher-level where the neuron recorded the long-term context.

    元の言語English
    ホスト出版物のタイトルProceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018
    編集者Suresh Sundaram
    出版者Institute of Electrical and Electronics Engineers Inc.
    ページ160-167
    ページ数8
    ISBN(電子版)9781538692769
    DOI
    出版物ステータスPublished - 2019 1 28
    イベント8th IEEE Symposium Series on Computational Intelligence, SSCI 2018 - Bangalore, India
    継続期間: 2018 11 182018 11 21

    出版物シリーズ

    名前Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018

    Conference

    Conference8th IEEE Symposium Series on Computational Intelligence, SSCI 2018
    India
    Bangalore
    期間18/11/1818/11/21

    Fingerprint

    Encoding
    Coding
    Term
    Neurons
    Brain
    Image Sequence
    Neural Network Model
    Model
    Neural networks
    Artificial Neural Network
    Neuron
    Update
    Predict
    Scenarios
    Motion
    Prediction
    Experiments
    Experiment

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Theoretical Computer Science

    これを引用

    Zhong, J., Ogata, T., & Cangelosi, A. (2019). Encoding Longer-term Contextual Sensorimotor Information in a Predictive Coding Model. : S. Sundaram (版), Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018 (pp. 160-167). [8628911] (Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSCI.2018.8628911

    Encoding Longer-term Contextual Sensorimotor Information in a Predictive Coding Model. / Zhong, Junpei; Ogata, Tetsuya; Cangelosi, Angelo.

    Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018. 版 / Suresh Sundaram. Institute of Electrical and Electronics Engineers Inc., 2019. p. 160-167 8628911 (Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018).

    研究成果: Conference contribution

    Zhong, J, Ogata, T & Cangelosi, A 2019, Encoding Longer-term Contextual Sensorimotor Information in a Predictive Coding Model. : S Sundaram (版), Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018., 8628911, Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018, Institute of Electrical and Electronics Engineers Inc., pp. 160-167, 8th IEEE Symposium Series on Computational Intelligence, SSCI 2018, Bangalore, India, 18/11/18. https://doi.org/10.1109/SSCI.2018.8628911
    Zhong J, Ogata T, Cangelosi A. Encoding Longer-term Contextual Sensorimotor Information in a Predictive Coding Model. : Sundaram S, 編集者, Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 160-167. 8628911. (Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018). https://doi.org/10.1109/SSCI.2018.8628911
    Zhong, Junpei ; Ogata, Tetsuya ; Cangelosi, Angelo. / Encoding Longer-term Contextual Sensorimotor Information in a Predictive Coding Model. Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018. 編集者 / Suresh Sundaram. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 160-167 (Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018).
    @inproceedings{92f32760dbaa4df699d5330ac2fb5559,
    title = "Encoding Longer-term Contextual Sensorimotor Information in a Predictive Coding Model",
    abstract = "Studies suggest that the difference of the sensorimotor events can be recorded with the fast- and slower-changing neural activities in the hierarchical brain areas, in which they have bi-directional connections. The slow-changing representations attempt to predict the activities on the faster level by relaying categorized sensorimotor events. On the other hand, the incoming sensory information corrects such event-based prediction on the higher level by the novel or surprising signal. From this motivation, we propose a predictive hierarchical artificial neural network model which is implemented the differentiated temporal parameters for neural updates. Also, both the fast- and slow-changing neural activities are modulated by the active motor activities. This model is examined in the driving dataset, recorded in various events, which incorporates the image sequences and the ego-motion of the vehicle. Experiments show that the model encodes the driving scenarios on the higher-level where the neuron recorded the long-term context.",
    author = "Junpei Zhong and Tetsuya Ogata and Angelo Cangelosi",
    year = "2019",
    month = "1",
    day = "28",
    doi = "10.1109/SSCI.2018.8628911",
    language = "English",
    series = "Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    pages = "160--167",
    editor = "Suresh Sundaram",
    booktitle = "Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018",

    }

    TY - GEN

    T1 - Encoding Longer-term Contextual Sensorimotor Information in a Predictive Coding Model

    AU - Zhong, Junpei

    AU - Ogata, Tetsuya

    AU - Cangelosi, Angelo

    PY - 2019/1/28

    Y1 - 2019/1/28

    N2 - Studies suggest that the difference of the sensorimotor events can be recorded with the fast- and slower-changing neural activities in the hierarchical brain areas, in which they have bi-directional connections. The slow-changing representations attempt to predict the activities on the faster level by relaying categorized sensorimotor events. On the other hand, the incoming sensory information corrects such event-based prediction on the higher level by the novel or surprising signal. From this motivation, we propose a predictive hierarchical artificial neural network model which is implemented the differentiated temporal parameters for neural updates. Also, both the fast- and slow-changing neural activities are modulated by the active motor activities. This model is examined in the driving dataset, recorded in various events, which incorporates the image sequences and the ego-motion of the vehicle. Experiments show that the model encodes the driving scenarios on the higher-level where the neuron recorded the long-term context.

    AB - Studies suggest that the difference of the sensorimotor events can be recorded with the fast- and slower-changing neural activities in the hierarchical brain areas, in which they have bi-directional connections. The slow-changing representations attempt to predict the activities on the faster level by relaying categorized sensorimotor events. On the other hand, the incoming sensory information corrects such event-based prediction on the higher level by the novel or surprising signal. From this motivation, we propose a predictive hierarchical artificial neural network model which is implemented the differentiated temporal parameters for neural updates. Also, both the fast- and slow-changing neural activities are modulated by the active motor activities. This model is examined in the driving dataset, recorded in various events, which incorporates the image sequences and the ego-motion of the vehicle. Experiments show that the model encodes the driving scenarios on the higher-level where the neuron recorded the long-term context.

    UR - http://www.scopus.com/inward/record.url?scp=85062767836&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85062767836&partnerID=8YFLogxK

    U2 - 10.1109/SSCI.2018.8628911

    DO - 10.1109/SSCI.2018.8628911

    M3 - Conference contribution

    AN - SCOPUS:85062767836

    T3 - Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018

    SP - 160

    EP - 167

    BT - Proceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018

    A2 - Sundaram, Suresh

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -