Nature Communications (May 2017)

Generic decoding of seen and imagined objects using hierarchical visual features

  • Tomoyasu Horikawa,
  • Yukiyasu Kamitani

DOI
https://doi.org/10.1038/ncomms15037
Journal volume & issue
Vol. 8, no. 1
pp. 1 – 15

Abstract

Read online

Machine learning algorithms can decode objects that people see or imagine from their brain activity. Here the authors present a predictive decoder combined with deep neural network representations that generalizes beyond the training set and correctly identifies novel objects that it has never been trained on.