Bowers et al. eloquently describe issues with current deep neural network (DNN) models of vision, claiming that there are deficits both with the methods of assessment, and with the models themselves. I am in agreement with both these claims, but propose a different recipe to the one outlined in the target article for overcoming these issues.

Page is to be congratulated for challenging some misconceptions about neural representation. However, his target article, and the commentaries to it, highlight that the terms “local” and “distributed” are open to misinterpretation. These terms provide a poor description of neural coding strategies and a better taxonomy might resolve some of the issues.