Article

High-performing neural network models of visual cortex benefit from high latent dimensionality

2022-07-13

Abstract excerpt

Geometric descriptions of deep neural networks (DNNs) have the potential to uncover core representational principles of computational models in neuroscience. Here we examined the geometry of DNN models of visual cortex by quantifying the latent dimensionality of their natural image representations. A popular view holds that optimal DNNs compress their representations onto low-dimensional subspaces to achieve invar...

Topics

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

Identifiers and source

Literature Corpus work: eea27815-c66b-58f2-ad49-0fa818351ac3
DOI: 10.1101/2022.07.13.499969

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

High-performing neural network models of visual cortex benefit from high latent dimensionalityDOI 10.1101/2022.07.13.499969Read

Multidimensional dynamics of object representations in the human visual systemSemantic proximity Read

The representational geometry of out‐of‐distribution generalization in primary visual cortex and artificial neural networksSemantic proximity Read

Emergence of Visual Center-Periphery Spatial Organization in Deep Convolutional Neural NetworksSemantic proximity Read

Biological convolutions improve DNN robustness to noise and generalisationSemantic proximity Read

Hierarchical Emergence Profiles of Human-Derived Dimensions are a Fundamental Property of Deep Neural NetworksSemantic proximity Read

Divergent specializations for motion-driven representations in higher lateral and dorsal visual areasSemantic proximity Read

Understanding transformation tolerant visual object representations in the human brain and convolutional neural networksSemantic proximity Read

Deep Problems with Neural Network Models of Human VisionSemantic proximity Read

Cross-cue reconstruction of perceived 3D object structure from human visual cortexSemantic proximity Read

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

Large-scale hyperparameter search for predicting human brain responses in the Algonauts challengeSemantic proximity Read

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