{"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/known-unknowns-uncertainty-quality-in","title":"Known Unknowns: Uncertainty Quality in Bayesian Neural Networks","arxiv_id":"1612.01251","date":"2016-12-05","proceeding":null,"authors":["Ramon Oliveira","Pedro Tabacof","Eduardo Valle"],"abstract":"We evaluate the uncertainty quality in neural networks using anomaly\ndetection. We extract uncertainty measures (e.g. entropy) from the predictions\nof candidate models, use those measures as features for an anomaly detector,\nand gauge how well the detector differentiates known from unknown classes. We\nassign higher uncertainty quality to candidate models that lead to better\ndetectors. We also propose a novel method for sampling a variational\napproximation of a Bayesian neural network, called One-Sample Bayesian\nApproximation (OSBA). We experiment on two datasets, MNIST and CIFAR10. We\ncompare the following candidate neural network models: Maximum Likelihood,\nBayesian Dropout, OSBA, and --- for MNIST --- the standard variational\napproximation. We show that Bayesian Dropout and OSBA provide better\nuncertainty information than Maximum Likelihood, and are essentially equivalent\nto the standard variational approximation, but much faster.","url_abs":"http://arxiv.org/abs/1612.01251v2","url_pdf":"http://arxiv.org/pdf/1612.01251v2.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":"known-unknowns-uncertainty-quality-in","repo_url":"https://github.com/ramon-oliveira/deepstats","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"known-unknowns","task_name":"Known Unknowns"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1612.01251","atlas_url":"https://app.syntology.ai/?focus=1612.01251","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":"1612.01251"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1612.01251\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1612.01251"},"call":"get_concepts_for_paper(arxiv_id=\"1612.01251\")"}],"by_repo":[{"repo":"ramon-oliveira/deepstats","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":"b69c4dc64a1b061263513a1a075073a405d0d235db177a1ac625cdc8d5ff6a6b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}