Towards Biologically Plausible Artificial Vision

Behavioral and Brain Sciences (forthcoming)
  Copy   BIBTEX

Abstract

Quilty-Dunn et al. argue that DCNNs optimized for image classification exemplify structural disanalogies to human vision. A different kind of artificial vision—found in reinforcement learning agents navigating artificial three-dimensional environments—can be expected to be more human-like. Recent work suggests that language-like representations substantially improves these agents’ performance, lending some indirect support to the LoTH.

Author's Profile

Mason Westfall
Washington University in St. Louis

Analytics

Added to PP
2023-05-19

Downloads
46 (#75,207)

6 months
46 (#37,058)

Historical graph of downloads since first upload
This graph includes both downloads from PhilArchive and clicks on external links on PhilPapers.
How can I increase my downloads?