Article

The representational geometry of out‐of‐distribution generalization in primary visual cortex and artificial neural networks

2025-04-25

Abstract excerpt

Humans and other animals display a remarkable ability to generalize learned knowledge to novel domains, a phenomenon known as out-of-distribution (OOD) generalization. This capability is thought to depend on the format of neural population representations; however, the specific geometrical properties that support OOD generalization and the learning objectives that give rise to them remain poorly understood. Here,...

Topics

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

Identifiers and source

Literature Corpus work: cfd192b7-f826-5508-bad6-be665753d2d5
DOI: 10.1101/2025.04.23.650305

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

The representational geometry of out‐of‐distribution generalization in primary visual cortex and artificial neural networksDOI 10.1101/2025.04.23.650305Read

High-performing neural network models of visual cortex benefit from high latent dimensionalitySemantic proximity Read

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

Abstract representations emerge naturally in neural networks trained to perform multiple tasksSemantic proximity Read

Memory reactivation induces generalized visual learning and top-down propagated cortical plasticitySemantic proximity Read

Sparse coding models predict a spectral bias in the development of primary visual cortex (V1) receptive fieldsSemantic proximity Read

Biological convolutions improve DNN robustness to noise and generalisationSemantic proximity Read

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

How the visual brain can learn to parse images using a multiscale, incremental grouping processSemantic proximity Read

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

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

Learning to See Like a Child: Why Viewpoint Diversity is Fundamental for Human-Aligned Object RecognitionSemantic proximity Read

Attention Improves Population Codes by Warping Neural Manifolds in Human Visual CortexSemantic proximity Read