{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/shared-representational-geometry-across","title":"Shared Representational Geometry Across Neural Networks","arxiv_id":"1811.11684","date":"2018-11-28","proceeding":null,"authors":["Qihong Lu","Po-Hsuan Chen","Jonathan W. Pillow","Peter J. Ramadge","Kenneth A. Norman","Uri Hasson"],"abstract":"Different neural networks trained on the same dataset often learn similar\ninput-output mappings with very different weights. Is there some correspondence\nbetween these neural network solutions? For linear networks, it has been shown\nthat different instances of the same network architecture encode the same\nrepresentational similarity matrix, and their neural activity patterns are\nconnected by orthogonal transformations. However, it is unclear if this holds\nfor non-linear networks. Using a shared response model, we show that different\nneural networks encode the same input examples as different orthogonal\ntransformations of an underlying shared representation. We test this claim\nusing both standard convolutional neural networks and residual networks on\nCIFAR10 and CIFAR100.","url_abs":"http://arxiv.org/abs/1811.11684v2","url_pdf":"http://arxiv.org/pdf/1811.11684v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"shared-representational-geometry-across","repo_url":"https://github.com/qihongl/nnsrm-neurips18","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"shared-representational-geometry-across","repo_url":"https://github.com/qihongl/demo-nnalign","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}