{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Farahat A"],"funding":["European Research Council"],"pagination":["400-414"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC7616855"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["167"],"pubmed_abstract":["Convolutional neural networks (CNNs) are one of the most successful computer vision systems to solve object recognition. Furthermore, CNNs have major applications in understanding the nature of visual representations in the human brain. Yet it remains poorly understood how CNNs actually make their decisions, what the nature of their internal representations is, and how their recognition strategies differ from humans. Specifically, there is a major debate about the question of whether CNNs primarily rely on surface regularities of objects, or whether they are capable of exploiting the spatial arrangement of features, similar to humans. Here, we develop a novel feature-scrambling approach to explicitly test whether CNNs use the spatial arrangement of features (i.e. object parts) to classify "],"journal":["Neural networks : the official journal of the International Neural Network Society"],"pubmed_title":["A novel feature-scrambling approach reveals the capacity of convolutional neural networks to learn spatial relations."],"pmcid":["PMC7616855"],"funding_grant_id":["850861"],"pubmed_authors":["Vinck M","Effenberger F","Farahat A"],"additional_accession":[]},"is_claimable":false,"name":"A novel feature-scrambling approach reveals the capacity of convolutional neural networks to learn spatial relations.","description":"Convolutional neural networks (CNNs) are one of the most successful computer vision systems to solve object recognition. Furthermore, CNNs have major applications in understanding the nature of visual representations in the human brain. Yet it remains poorly understood how CNNs actually make their decisions, what the nature of their internal representations is, and how their recognition strategies differ from humans. Specifically, there is a major debate about the question of whether CNNs primarily rely on surface regularities of objects, or whether they are capable of exploiting the spatial arrangement of features, similar to humans. Here, we develop a novel feature-scrambling approach to explicitly test whether CNNs use the spatial arrangement of features (i.e. object parts) to classify ","dates":{"release":"2023-01-01T00:00:00Z","publication":"2023 Oct","modification":"2025-04-18T12:57:02.047Z","creation":"2025-04-06T22:23:42.398Z"},"accession":"S-EPMC7616855","cross_references":{"pubmed":["37673027"],"doi":["10.1016/j.neunet.2023.08.021"]}}