Deep Neural Networks Can Learn Generalizable Same-Different Visual Relations

no code implementations • 14 Oct 2023 • Alexa R. Tartaglini, Sheridan Feucht, Michael A. Lepori, Wai Keen Vong, Charles Lovering, Brenden M. Lake, Ellie Pavlick

Much of this prior work focuses on training convolutional neural networks to classify images of two same or two different abstract shapes, testing generalization on within-distribution stimuli.

Object Recognition Out-of-Distribution Generalization

A Developmentally-Inspired Examination of Shape versus Texture Bias in Machines

1 code implementation • 16 Feb 2022 • Alexa R. Tartaglini, Wai Keen Vong, Brenden M. Lake

In this work, we re-examine the inductive biases of neural networks by adapting the stimuli and procedure from Geirhos et al. (2019) to more closely follow the developmental paradigm and test on a wide range of pre-trained neural networks.