Deep neural networks are not a single hypothesis but a language for expressing computational hypotheses

Tal Golan, JohnMark Taylor, Heiko Schütt, Benjamin Peters, Rowan P. Sommers, Katja Seeliger, Adrien Doerig, Paul Linton, Talia Konkle, Marcel van Gerven, Konrad Kording, Blake Richards, Tim C. Kietzmann, Grace W. Lindsay, Nikolaus Kriegeskorte

Abstract: An ideal vision model accounts for behavior and neurophysiology in both naturalistic conditions and designed lab experiments. Unlike psychological theories, artificial neural networks (ANNs) actually perform visual tasks and generate testable predictions for arbitrary inputs. These advantages enable ANNs to engage the entire spectrum of the evidence. Failures of particular models drive progress in a vibrant ANN research program of human vision.

External IDs:doi:10.1017/s0140525x23001553