{"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/the-emergence-of-organizing-structure-in","title":"The Emergence of Organizing Structure in Conceptual Representation","arxiv_id":"1611.09384","date":"2016-11-28","proceeding":null,"authors":["Brenden M. Lake","Neil D. Lawrence","Joshua B. Tenenbaum"],"abstract":"Both scientists and children make important structural discoveries, yet their\ncomputational underpinnings are not well understood. Structure discovery has\npreviously been formalized as probabilistic inference about the right\nstructural form --- where form could be a tree, ring, chain, grid, etc. [Kemp &\nTenenbaum (2008). The discovery of structural form. PNAS, 105(3), 10687-10692].\nWhile this approach can learn intuitive organizations, including a tree for\nanimals and a ring for the color circle, it assumes a strong inductive bias\nthat considers only these particular forms, and each form is explicitly\nprovided as initial knowledge. Here we introduce a new computational model of\nhow organizing structure can be discovered, utilizing a broad hypothesis space\nwith a preference for sparse connectivity. Given that the inductive bias is\nmore general, the model's initial knowledge shows little qualitative\nresemblance to some of the discoveries it supports. As a consequence, the model\ncan also learn complex structures for domains that lack intuitive description,\nas well as predict human property induction judgments without explicit\nstructural forms. By allowing form to emerge from sparsity, our approach\nclarifies how both the richness and flexibility of human conceptual\norganization can coexist.","url_abs":"http://arxiv.org/abs/1611.09384v2","url_pdf":"http://arxiv.org/pdf/1611.09384v2.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":"the-emergence-of-organizing-structure-in","repo_url":"https://github.com/brendenlake/structural-sparsity","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"form","task_name":"Form"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}