{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/learning-inductive-biases-with-simple-neural","title":"Learning Inductive Biases with Simple Neural Networks","arxiv_id":"1802.02745","date":"2018-02-08","proceeding":null,"authors":["Reuben Feinman","Brenden M. Lake"],"abstract":"People use rich prior knowledge about the world in order to efficiently learn\nnew concepts. These priors - also known as \"inductive biases\" - pertain to the\nspace of internal models considered by a learner, and they help the learner\nmake inferences that go beyond the observed data. A recent study found that\ndeep neural networks optimized for object recognition develop the shape bias\n(Ritter et al., 2017), an inductive bias possessed by children that plays an\nimportant role in early word learning. However, these networks use\nunrealistically large quantities of training data, and the conditions required\nfor these biases to develop are not well understood. Moreover, it is unclear\nhow the learning dynamics of these networks relate to developmental processes\nin childhood. We investigate the development and influence of the shape bias in\nneural networks using controlled datasets of abstract patterns and synthetic\nimages, allowing us to systematically vary the quantity and form of the\nexperience provided to the learning algorithms. We find that simple neural\nnetworks develop a shape bias after seeing as few as 3 examples of 4 object\ncategories. The development of these biases predicts the onset of vocabulary\nacceleration in our networks, consistent with the developmental process in\nchildren.","url_abs":"http://arxiv.org/abs/1802.02745v2","url_pdf":"http://arxiv.org/pdf/1802.02745v2.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":"learning-inductive-biases-with-simple-neural","repo_url":"https://github.com/rfeinman/learning-to-learn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.02745","atlas_url":"https://app.syntology.ai/?focus=1802.02745","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1802.02745"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1802.02745\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1802.02745"},"call":"get_concepts_for_paper(arxiv_id=\"1802.02745\")"}],"by_repo":[{"repo":"rfeinman/learning-to-learn","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d0fcf6cdc8a108a56c8f0d1ef39b918c5c233792b628f33949fb17c0a37cc25a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}