Skip to main content
Duke University Libraries
View Item 
  •   DukeSpace
  • Duke Scholarly Works
  • Scholarly Articles
  • View Item
  •   DukeSpace
  • Duke Scholarly Works
  • Scholarly Articles
  • View Item
    • Login
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Neuroprosthetic Decoder Training as Imitation Learning.

    Thumbnail
    Files
    1511.04156v2.pdf
    926.4 Kb
    Neuroprosthetic Decoder Training as Imitation Learning.pdf
    1.5 Mb
    Date
    2018-02-02
    Authors
    Carlson, D
    Cunningham, JP
    Merel, J
    Paninski, Liam
    Repository Usage Stats
    255
    views
    81
    downloads
    Abstract
    Neuroprosthetic brain-computer interfaces function via an algorithm which decodes neural activity of the user into movements of an end effector, such as a cursor or robotic arm. In practice, the decoder is often learned by updating its parameters while the user performs a task. When the user's intention is not directly observable, recent methods have demonstrated value in training the decoder against a surrogate for the user's intended movement. Here we show that training a decoder in this way is a novel variant of an imitation learning problem, where an oracle or expert is employed for supervised training in lieu of direct observations, which are not available. Specifically, we describe how a generic imitation learning meta-algorithm, dataset aggregation (DAgger), can be adapted to train a generic brain-computer interface. By deriving existing learning algorithms for brain-computer interfaces in this framework, we provide a novel analysis of regret (an important metric of learning efficacy) for brain-computer interfaces. This analysis allows us to characterize the space of algorithmic variants and bounds on their regret rates. Existing approaches for decoder learning have been performed in the cursor control setting, but the available design principles for these decoders are such that it has been impossible to scale them to naturalistic settings. Leveraging our findings, we then offer an algorithm that combines imitation learning with optimal control, which should allow for training of arbitrary effectors for which optimal control can generate goal-oriented control. We demonstrate this novel and general BCI algorithm with simulated neuroprosthetic control of a 26 degree-of-freedom model of an arm, a sophisticated and realistic end effector.
    Type
    Journal article
    Subject
    Algorithms
    Arm
    Brain-Computer Interfaces
    Computational Biology
    Computer Simulation
    Humans
    Learning
    Robotics
    Supervised Machine Learning
    Task Performance and Analysis
    Permalink
    https://hdl.handle.net/10161/16068
    Published Version (Please cite this version)
    10.1371/journal.pcbi.1004948
    Publication Info
    Carlson, D; Cunningham, JP; Merel, J; & Paninski, Liam (2018). Neuroprosthetic Decoder Training as Imitation Learning. PLoS Comput Biol, 12(5). pp. e1004948. 10.1371/journal.pcbi.1004948. Retrieved from https://hdl.handle.net/10161/16068.
    This is constructed from limited available data and may be imprecise. To cite this article, please review & use the official citation provided by the journal.
    Collections
    • Scholarly Articles
    More Info
    Show full item record
    Open Access

    Articles written by Duke faculty are made available through the campus open access policy. For more information see: Duke Open Access Policy

    Rights for Collection: Scholarly Articles

     

     

    Search Scope

    Browse

    All of DukeSpaceCommunities & CollectionsAuthorsTitlesTypesBy Issue DateDepartmentsAffiliations of Duke Author(s)SubjectsBy Submit DateThis CollectionAuthorsTitlesTypesBy Issue DateDepartmentsAffiliations of Duke Author(s)SubjectsBy Submit Date

    My Account

    LoginRegister

    Statistics

    View Usage Statistics