{"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/uncertainty-in-neural-networks-bayesian","title":"Uncertainty in Neural Networks: Approximately Bayesian Ensembling","arxiv_id":"1810.05546","date":"2018-10-12","proceeding":null,"authors":["Tim Pearce","Felix Leibfried","Alexandra Brintrup","Mohamed Zaki","Andy Neely"],"abstract":"Understanding the uncertainty of a neural network's (NN) predictions is essential for many purposes. The Bayesian framework provides a principled approach to this, however applying it to NNs is challenging due to large numbers of parameters and data. Ensembling NNs provides an easily implementable, scalable method for uncertainty quantification, however, it has been criticised for not being Bayesian. This work proposes one modification to the usual process that we argue does result in approximate Bayesian inference; regularising parameters about values drawn from a distribution which can be set equal to the prior. A theoretical analysis of the procedure in a simplified setting suggests the recovered posterior is centred correctly but tends to have an underestimated marginal variance, and overestimated correlation. However, two conditions can lead to exact recovery. We argue that these conditions are partially present in NNs. Empirical evaluations demonstrate it has an advantage over standard ensembling, and is competitive with variational methods.","url_abs":"https://arxiv.org/abs/1810.05546v5","url_pdf":"https://arxiv.org/pdf/1810.05546v5.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":"uncertainty-in-neural-networks-bayesian","repo_url":"https://github.com/TeaPearce/Bayesian_NN_Ensembles","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"uncertainty-in-neural-networks-bayesian","repo_url":"https://github.com/giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.05546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.05546"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TeaPearce/Bayesian_NN_Ensembles","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":16},"by_repo_kind":{"official":{"samples":8,"ran":0,"repositories":1},"listed":{"samples":8,"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":"049d2ff8e0580c54","entry":"data_training","repo":"giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms","repo_kind":"listed","path":"training_step.py","file_url":"https://github.com/giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms/blob/HEAD/training_step.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"049d2ff8e0580c54"}},{"code_sha256_prefix":"9170211e7fedd09e","entry":"epsilon_greedy_policy","repo":"giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms","repo_kind":"listed","path":"play_one_step.py","file_url":"https://github.com/giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms/blob/HEAD/play_one_step.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9170211e7fedd09e"}},{"code_sha256_prefix":"1915bcf3c5c8ecb4","entry":"fn_my_loss","repo":"TeaPearce/Bayesian_NN_Ensembles","repo_kind":"official","path":"classification/2d_class_need_03.py","file_url":"https://github.com/TeaPearce/Bayesian_NN_Ensembles/blob/HEAD/classification/2d_class_need_03.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1915bcf3c5c8ecb4"}},{"code_sha256_prefix":"a1a896e5eded3920","entry":"get_action","repo":"giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms","repo_kind":"listed","path":"play_one_step.py","file_url":"https://github.com/giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms/blob/HEAD/play_one_step.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a1a896e5eded3920"}},{"code_sha256_prefix":"58ed8144cb697424","entry":"get_hyperparams","repo":"TeaPearce/Bayesian_NN_Ensembles","repo_kind":"official","path":"regression/hyperparams.py","file_url":"https://github.com/TeaPearce/Bayesian_NN_Ensembles/blob/HEAD/regression/hyperparams.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"58ed8144cb697424"}},{"code_sha256_prefix":"21f05dc03145f0ba","entry":"half_cheetah_cost_fn","repo":"giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms","repo_kind":"listed","path":"cost_functions.py","file_url":"https://github.com/giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms/blob/HEAD/cost_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"21f05dc03145f0ba"}},{"code_sha256_prefix":"41dd6f9037d680b6","entry":"inverted_pendulum_cost_fn","repo":"giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms","repo_kind":"listed","path":"cost_functions.py","file_url":"https://github.com/giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms/blob/HEAD/cost_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"41dd6f9037d680b6"}},{"code_sha256_prefix":"626f3d6baf7dc55b","entry":"lr_schedule","repo":"TeaPearce/Bayesian_NN_Ensembles","repo_kind":"official","path":"classification/2d_class_need_03.py","file_url":"https://github.com/TeaPearce/Bayesian_NN_Ensembles/blob/HEAD/classification/2d_class_need_03.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"626f3d6baf7dc55b"}},{"code_sha256_prefix":"6802e5d7fe4d2d58","entry":"np_k_0","repo":"TeaPearce/Bayesian_NN_Ensembles","repo_kind":"official","path":"regression/module_gp.py","file_url":"https://github.com/TeaPearce/Bayesian_NN_Ensembles/blob/HEAD/regression/module_gp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6802e5d7fe4d2d58"}},{"code_sha256_prefix":"e8ccab56c21c75ce","entry":"np_softmax","repo":"TeaPearce/Bayesian_NN_Ensembles","repo_kind":"official","path":"classification/2d_class_need_03.py","file_url":"https://github.com/TeaPearce/Bayesian_NN_Ensembles/blob/HEAD/classification/2d_class_need_03.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e8ccab56c21c75ce"}},{"code_sha256_prefix":"7796962d8760fb27","entry":"np_step","repo":"TeaPearce/Bayesian_NN_Ensembles","repo_kind":"official","path":"regression/module_gp.py","file_url":"https://github.com/TeaPearce/Bayesian_NN_Ensembles/blob/HEAD/regression/module_gp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7796962d8760fb27"}},{"code_sha256_prefix":"c3529256b7b082a6","entry":"np_step_kernel","repo":"TeaPearce/Bayesian_NN_Ensembles","repo_kind":"official","path":"regression/module_gp.py","file_url":"https://github.com/TeaPearce/Bayesian_NN_Ensembles/blob/HEAD/regression/module_gp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c3529256b7b082a6"}},{"code_sha256_prefix":"ca3901c6b47a2a0a","entry":"pendulum_cost_fn","repo":"giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms","repo_kind":"listed","path":"cost_functions.py","file_url":"https://github.com/giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms/blob/HEAD/cost_functions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca3901c6b47a2a0a"}},{"code_sha256_prefix":"8839f6d395bca7bf","entry":"play_one_step","repo":"giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms","repo_kind":"listed","path":"play_one_step.py","file_url":"https://github.com/giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms/blob/HEAD/play_one_step.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8839f6d395bca7bf"}},{"code_sha256_prefix":"479d482abed0b4ff","entry":"sigmoid_array","repo":"TeaPearce/Bayesian_NN_Ensembles","repo_kind":"official","path":"regression/DataGen.py","file_url":"https://github.com/TeaPearce/Bayesian_NN_Ensembles/blob/HEAD/regression/DataGen.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"479d482abed0b4ff"}},{"code_sha256_prefix":"e55b7a835164bf52","entry":"training_step","repo":"giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms","repo_kind":"listed","path":"training_step.py","file_url":"https://github.com/giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms/blob/HEAD/training_step.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e55b7a835164bf52"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}