September 2024
Volume 24, Issue 10
Open Access
Vision Sciences Society Annual Meeting Abstract  |   September 2024
Multitask Machine Learning of Contrast Sensitivity Functions
Author Affiliations & Notes
  • Dennis Barbour
    Washington University in St. Louis
  • Zhiting Zhou
    Washington University in St. Louis
  • Dom Marticorena
    Washington University in St. Louis
  • Quinn Wai Wong
    Washington University in St. Louis
  • Jake Browning
    Washington University in St. Louis
  • Ken Wilbur
    Washington University in St. Louis
  • Pinakin Davey
    Western University of Health Sciences
  • Aaron Seitz
    Northeastern University
  • Jacob Gardner
    University of Pennsylvania
  • Footnotes
    Acknowledgements  R21-EY033553, R01-EY019693
Journal of Vision September 2024, Vol.24, 1082. doi:https://doi.org/10.1167/jov.24.10.1082
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Dennis Barbour, Zhiting Zhou, Dom Marticorena, Quinn Wai Wong, Jake Browning, Ken Wilbur, Pinakin Davey, Aaron Seitz, Jacob Gardner; Multitask Machine Learning of Contrast Sensitivity Functions. Journal of Vision 2024;24(10):1082. https://doi.org/10.1167/jov.24.10.1082.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Contrast Sensitivity Functions (CSFs) represent useful diagnostic adjuncts for helping assess both retinal and central visual functionality. Gaussian Process (GP) classifiers have been shown to efficiently estimate individual CSF models by leveraging active machine learning for optimal stimulus selection. Model convergence in these cases can be achieved with between 10 and 50 actively selected stimuli. By assuming model independence, this disjoint process requires sequential estimation to obtain CSF models for multiple eyes or stimulus conditions (e.g., luminance, eccentricity). Conjoint estimators, on the other hand, have now been developed to estimate multiple CSFs simultaneously using an active multitask implementation. In the current study, conjoint CSF estimator performance was compared to disjoint performance on simulated eyes using generative models created from human data. The high degree of expected similarity between CSFs originating from different eyes or conditions allows conjoint learning between the related models. This procedure is designed to enable faster convergence than sequential disjoint model learning. Indeed, conjoint CSF estimation does speed model convergence over disjoint estimation under commonly encountered scenarios. These findings confirm that incorporation of additional information beyond immediate behavioral responses into new machine learning models of vision functions may improve visual system assessment.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×