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

Junpei Zhong, Tetsuya Ogata, Angelo Cangelosi

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

    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.

    Original languageEnglish
    Title of host publicationProceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018
    EditorsSuresh Sundaram
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages160-167
    Number of pages8
    ISBN (Electronic)9781538692769
    DOIs
    Publication statusPublished - 2019 Jan 28
    Event8th IEEE Symposium Series on Computational Intelligence, SSCI 2018 - Bangalore, India
    Duration: 2018 Nov 182018 Nov 21

    Publication series

    NameProceedings of the 2018 IEEE Symposium Series on Computational Intelligence, SSCI 2018

    Conference

    Conference8th IEEE Symposium Series on Computational Intelligence, SSCI 2018
    CountryIndia
    CityBangalore
    Period18/11/1818/11/21

    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

    Cite this

    Zhong, J., Ogata, T., & Cangelosi, A. (2019). Encoding Longer-term Contextual Sensorimotor Information in a Predictive Coding Model. In S. Sundaram (Ed.), 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. ed. / 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).

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

    Zhong, J, Ogata, T & Cangelosi, A 2019, Encoding Longer-term Contextual Sensorimotor Information in a Predictive Coding Model. in S Sundaram (ed.), 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. In Sundaram S, editor, 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. editor / 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

    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 -