Article

Hierarchical Emergence Profiles of Human-Derived Dimensions are a Fundamental Property of Deep Neural Networks

2025-05-21

Abstract excerpt

Object recognition in the human visual system is implemented within a hierarchy characterised by increasing feature complexity. Here, we investigated whether human-derived dimensions of object knowledge show a similar progressive emergence across layers in deep neural networks (DNNs), and how this emergence is shaped by architecture, learning objective, and stimulus statistics. To test this, we predicted human-der...

Topics

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

Identifiers and source

Literature Corpus work: 10a376b1-8947-568e-a423-1cce7e0c05be
DOI: 10.1101/2025.05.19.654977

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Hierarchical Emergence Profiles of Human-Derived Dimensions are a Fundamental Property of Deep Neural NetworksDOI 10.1101/2025.05.19.654977Read

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

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

Gradual sensory maturation promotes abstract representation learningSemantic proximity Read

Shared Representations of Stability in Humans, Supervised & Unsupervised Deep Neural NetworksSemantic proximity Read

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

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

A single computational objective can produce specialization of streams in visual cortexSemantic proximity Read

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

A controller-peripheral architecture and costly energy principle for learningSemantic proximity Read

Leveraging prior concept learning improves ability to generalize from few examples in computational models of human object recognitionSemantic proximity Read

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

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