{"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/reliable-uncertainty-estimates-in-deep-neural","title":"Noise Contrastive Priors for Functional Uncertainty","arxiv_id":"1807.09289","date":"2018-07-24","proceeding":"ICLR 2019 5","authors":["Danijar Hafner","Dustin Tran","Timothy Lillicrap","Alex Irpan","James Davidson"],"abstract":"Obtaining reliable uncertainty estimates of neural network predictions is a long standing challenge. Bayesian neural networks have been proposed as a solution, but it remains open how to specify their prior. In particular, the common practice of an independent normal prior in weight space imposes relatively weak constraints on the function posterior, allowing it to generalize in unforeseen ways on inputs outside of the training distribution. We propose noise contrastive priors (NCPs) to obtain reliable uncertainty estimates. The key idea is to train the model to output high uncertainty for data points outside of the training distribution. NCPs do so using an input prior, which adds noise to the inputs of the current mini batch, and an output prior, which is a wide distribution given these inputs. NCPs are compatible with any model that can output uncertainty estimates, are easy to scale, and yield reliable uncertainty estimates throughout training. Empirically, we show that NCPs prevent overfitting outside of the training distribution and result in uncertainty estimates that are useful for active learning. We demonstrate the scalability of our method on the flight delays data set, where we significantly improve upon previously published results.","url_abs":"https://arxiv.org/abs/1807.09289v3","url_pdf":"https://arxiv.org/pdf/1807.09289v3.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":"reliable-uncertainty-estimates-in-deep-neural","repo_url":"https://github.com/data61/aboleth","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"reliable-uncertainty-estimates-in-deep-neural","repo_url":"https://github.com/brain-research/ncp","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.09289","atlas_url":"https://app.syntology.ai/?focus=1807.09289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.09289"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/data61/aboleth","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/brain-research/ncp","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":7,"ran":0,"repositories":1},"named_in_paper":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c9127148ca1a1a00","entry":"elbo","repo":"data61/aboleth","repo_kind":"official","path":"aboleth/losses.py","file_url":"https://github.com/data61/aboleth/blob/HEAD/aboleth/losses.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c9127148ca1a1a00"}},{"code_sha256_prefix":"2d9228c8f236855e","entry":"max_posterior","repo":"data61/aboleth","repo_kind":"official","path":"aboleth/losses.py","file_url":"https://github.com/data61/aboleth/blob/HEAD/aboleth/losses.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2d9228c8f236855e"}},{"code_sha256_prefix":"fa50b4848175e660","entry":"network","repo":"brain-research/ncp","repo_kind":"named_in_paper","path":"ncp/models/bbb.py","file_url":"https://github.com/brain-research/ncp/blob/HEAD/ncp/models/bbb.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fa50b4848175e660"}},{"code_sha256_prefix":"8be3852a7610c55b","entry":"network","repo":"brain-research/ncp","repo_kind":"named_in_paper","path":"ncp/models/det.py","file_url":"https://github.com/brain-research/ncp/blob/HEAD/ncp/models/det.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8be3852a7610c55b"}},{"code_sha256_prefix":"6e47e5845da92d6c","entry":"network","repo":"brain-research/ncp","repo_kind":"named_in_paper","path":"ncp/models/det_mix_ncp.py","file_url":"https://github.com/brain-research/ncp/blob/HEAD/ncp/models/det_mix_ncp.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6e47e5845da92d6c"}},{"code_sha256_prefix":"1aa70fc3b9f93b29","entry":"norm_prior","repo":"data61/aboleth","repo_kind":"official","path":"aboleth/distributions.py","file_url":"https://github.com/data61/aboleth/blob/HEAD/aboleth/distributions.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1aa70fc3b9f93b29"}},{"code_sha256_prefix":"743a9cde8e4a08b4","entry":"pos_variable","repo":"data61/aboleth","repo_kind":"official","path":"aboleth/util.py","file_url":"https://github.com/data61/aboleth/blob/HEAD/aboleth/util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"743a9cde8e4a08b4"}},{"code_sha256_prefix":"141e50bea465ebcf","entry":"sample_mean","repo":"data61/aboleth","repo_kind":"official","path":"aboleth/prediction.py","file_url":"https://github.com/data61/aboleth/blob/HEAD/aboleth/prediction.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"141e50bea465ebcf"}},{"code_sha256_prefix":"c61e992697a0729e","entry":"sample_model","repo":"data61/aboleth","repo_kind":"official","path":"aboleth/prediction.py","file_url":"https://github.com/data61/aboleth/blob/HEAD/aboleth/prediction.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c61e992697a0729e"}},{"code_sha256_prefix":"d4df2c6547157ed1","entry":"stack","repo":"data61/aboleth","repo_kind":"official","path":"aboleth/baselayers.py","file_url":"https://github.com/data61/aboleth/blob/HEAD/aboleth/baselayers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d4df2c6547157ed1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}