Neither hype nor gloom do DNNs justice
Related Experiment Video
Updated: Aug 9, 2026

Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
Felix A Wichmann1, Simon Kornblith2, Robert Geirhos2
1Neural Information Processing Group, University of Tübingen, Tübingen, Germany felix.wichmann@tuebingen.de.
Abstract:
Neither the hype exemplified in some exaggerated claims about deep neural networks (DNNs), nor the gloom expressed by Bowers et al. do DNNs as models in vision science justice: DNNs rapidly evolve, and today's limitations are often tomorrow's successes. In addition, providing explanations as well as prediction and image-computability are model desiderata; one should not be favoured at the expense of the other.
Related Concept Videos
Entropy
Nonsense-mediated mRNA Decay
Usually, Upf3 binds to an Exon Junction Complex (EJC) at mRNA splice sites. If a ribosome fully translates the mRNA,...
Nonsense-mediated mRNA Decay
Usually, Upf3 binds to an Exon Junction Complex (EJC) at mRNA splice sites. If a ribosome fully translates the mRNA,...
Entropy
When an ideal gas expands isothermally, the disorder in the gas increases. From the molecular perspective, the gas molecules have more volume to move around in.
Consider an infinitesimal step in the expansion, which...
Uncertainty: Overview
Unrealistic Optimism Bias

