Article

Deep Problems with Neural Network Models of Human Vision

2022-04-13

Abstract excerpt

<p>Deep neural networks (DNNs) have had extraordinary successes in classifying photographic images of objects and are often described as the best models of biological vision. This conclusion is largely based on three sets of findings: (1) DNNs are more accurate than any other model in classifying images taken from various datasets, (2) DNNs do the best job in predicting the pattern of human errors in classifying o...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 0d11daf8-2490-5730-8f74-1b48744b040f
DOI: 10.31234/osf.io/5zf4s

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Deep Problems with Neural Network Models of Human VisionDOI 10.31234/osf.io/5zf4sRead

Deep neural networks are not a single hypothesis but a language for expressing computational hypothesesSemantic proximity Read

Deep networks may capture biological behaviour for shallow, but not deep, empirical characterizationsSemantic proximity Read

Whether pattern memory can be truly realized in deep neural network?Semantic proximity Read

Biological convolutions improve DNN robustness to noise and generalisationSemantic proximity Read

Teaching deep networks to see shape: Lessons from a simplified visual worldSemantic proximity Read

To find better neural network models of human vision, find better neural network models of primate visionSemantic proximity Read

Grounding deep neural network predictions of human categorization behavior in understandable functional features: The case of face identitySemantic proximity Read

The role of capacity constraints in Convolutional Neural Networks for learning random versus natural dataSemantic proximity Read

The representational hierarchy in human and artificial visual systems in the presence of object-scene regularitiesSemantic proximity Read

Comparing Brain-Score and ImageNet performance with responses to the scintillating grid illusionSemantic proximity Read

Feature blindness: a challenge for understanding and modelling visual object recognitionSemantic proximity Read

A Feedforward Convolutional Neural Network Learns from Images to Covertly Attend to Contextual Cues like Human and Bayesian Ideal ObserversSemantic proximity Read