{"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/task-agnostic-continual-learning-using-online","title":"Task Agnostic Continual Learning Using Online Variational Bayes","arxiv_id":"1803.10123","date":"2018-03-27","proceeding":null,"authors":["Chen Zeno","Itay Golan","Elad Hoffer","Daniel Soudry"],"abstract":"Catastrophic forgetting is the notorious vulnerability of neural networks to\nthe change of the data distribution while learning. This phenomenon has long\nbeen considered a major obstacle for allowing the use of learning agents in\nrealistic continual learning settings. A large body of continual learning\nresearch assumes that task boundaries are known during training. However,\nresearch for scenarios in which task boundaries are unknown during training has\nbeen lacking. In this paper we present, for the first time, a method for\npreventing catastrophic forgetting (BGD) for scenarios with task boundaries\nthat are unknown during training --- task-agnostic continual learning. Code of\nour algorithm is available at https://github.com/igolan/bgd.","url_abs":"http://arxiv.org/abs/1803.10123v3","url_pdf":"http://arxiv.org/pdf/1803.10123v3.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":"task-agnostic-continual-learning-using-online","repo_url":"https://github.com/igolan/bgd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"task-agnostic-continual-learning-using-online","repo_url":"https://github.com/taldatech/tf-bgd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.10123","atlas_url":"https://app.syntology.ai/?focus=1803.10123","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.10123"}},"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/taldatech/tf-bgd","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/igolan/bgd","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":"e4de4e90f9014c20","entry":"adam","repo":"igolan/bgd","repo_kind":"official","path":"optimizers_lib/optimizers_lib.py","file_url":"https://github.com/igolan/bgd/blob/HEAD/optimizers_lib/optimizers_lib.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":"e4de4e90f9014c20"}},{"code_sha256_prefix":"996f532d849dc656","entry":"bgd","repo":"igolan/bgd","repo_kind":"official","path":"optimizers_lib/optimizers_lib.py","file_url":"https://github.com/igolan/bgd/blob/HEAD/optimizers_lib/optimizers_lib.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":"996f532d849dc656"}},{"code_sha256_prefix":"35b9edc57d88d973","entry":"calculate_gain","repo":"igolan/bgd","repo_kind":"official","path":"nn_utils/init_utils.py","file_url":"https://github.com/igolan/bgd/blob/HEAD/nn_utils/init_utils.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":"35b9edc57d88d973"}},{"code_sha256_prefix":"7017609a5ade3c7f","entry":"kaiming_normal_std_","repo":"igolan/bgd","repo_kind":"official","path":"nn_utils/init_utils.py","file_url":"https://github.com/igolan/bgd/blob/HEAD/nn_utils/init_utils.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":"7017609a5ade3c7f"}},{"code_sha256_prefix":"2a7a7a7286986fde","entry":"labels_trick","repo":"igolan/bgd","repo_kind":"official","path":"nn_utils/labels_trick.py","file_url":"https://github.com/igolan/bgd/blob/HEAD/nn_utils/labels_trick.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":"2a7a7a7286986fde"}},{"code_sha256_prefix":"184f03d97f32de50","entry":"sgd","repo":"igolan/bgd","repo_kind":"official","path":"optimizers_lib/optimizers_lib.py","file_url":"https://github.com/igolan/bgd/blob/HEAD/optimizers_lib/optimizers_lib.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":"184f03d97f32de50"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}