BIROn - Birkbeck Institutional Research Online

    Deep-learning networks and the functional architecture of executive control

    Cooper, Richard P. (2017) Deep-learning networks and the functional architecture of executive control. Behavioral and Brain Sciences 40 , e261. ISSN 0140-525X.

    [img]
    Preview
    Text
    18017.pdf - Author's Accepted Manuscript

    Download (364kB) | Preview

    Abstract

    Lake et al. underrate both the promise and the limitations of contemporary deep learning techniques. The promise lies in combining those techniques with broad multisensory training as experienced by infants and children. The limitations lie in the need for such systems to possess functional subsystems that generate, monitor and switch goals and strategies in the absence of human intervention.

    Metadata

    Item Type: Article
    School: Birkbeck Schools and Departments > School of Science > Psychological Sciences
    Research Centre: Cognition, Computation and Modelling, Centre for
    Depositing User: Richard Cooper
    Date Deposited: 01 Feb 2017 18:03
    Last Modified: 11 May 2018 00:10
    URI: http://eprints.bbk.ac.uk/id/eprint/18017

    Statistics

    Downloads
    Activity Overview
    59Downloads
    174Hits

    Additional statistics are available via IRStats2.

    Archive Staff Only (login required)

    Edit/View Item Edit/View Item