September 2017
Volume 17, Issue 10
Open Access
Vision Sciences Society Annual Meeting Abstract  |   August 2017
Unsupervised learning of repeating patterns using a novel STDP based algorithm
Author Affiliations
  • Simon Thorpe
    CerCo, CNRS
  • Amirreza Yousefzadeh
    Instituto Microelectronica de Sevilla, University of Sevilla
  • Jacob Martin
    CerCo, CNRS
  • Timothée Masquelier
    CerCo, CNRS
Journal of Vision August 2017, Vol.17, 1079. doi:https://doi.org/10.1167/17.10.1079
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Simon Thorpe, Amirreza Yousefzadeh, Jacob Martin, Timothée Masquelier; Unsupervised learning of repeating patterns using a novel STDP based algorithm. Journal of Vision 2017;17(10):1079. https://doi.org/10.1167/17.10.1079.

      Download citation file:


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

      ×
  • Supplements
Abstract

Computational vision systems that are trained with deep learning have recently matched human performance (Hinton et al). However, while deep learning typically requires tens or hundreds of thousands of labelled examples, humans can learn a task or stimulus with only a few repetitions. For example, a 2015 study by Andrillon et al. showed that human listeners can learn complicated random auditory noises after only a few repetitions, with each repetition invoking a larger and larger EEG activity than the previous. In addition, a 2015 study by Martin et al. showed that only 10 minutes of visual experience of a novel object class was required to change early EEG potentials, improve saccadic reaction times, and increase saccade accuracies for the particular object trained. How might such ultra-rapid learning actually be accomplished by the cortex? Here, we propose a simple unsupervised neural model based on spike timing dependent plasticity, which learns spatiotemporal patterns in visual or auditory stimuli with only a few repetitions. The model is attractive for applications because it is simple enough to allow the simulation of very large numbers of cortical neurons in real time. Theoretically, the model provides a plausible example of how the brain may accomplish rapid learning of repeating visual or auditory patterns using only a few examples.

Meeting abstract presented at VSS 2017

×
×

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.

×