{"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/lifelong-learning-of-spatiotemporal","title":"Lifelong Learning of Spatiotemporal Representations with Dual-Memory Recurrent Self-Organization","arxiv_id":"1805.10966","date":"2018-05-28","proceeding":null,"authors":["German I. Parisi","Jun Tani","Cornelius Weber","Stefan Wermter"],"abstract":"Artificial autonomous agents and robots interacting in complex environments\nare required to continually acquire and fine-tune knowledge over sustained\nperiods of time. The ability to learn from continuous streams of information is\nreferred to as lifelong learning and represents a long-standing challenge for\nneural network models due to catastrophic forgetting. Computational models of\nlifelong learning typically alleviate catastrophic forgetting in experimental\nscenarios with given datasets of static images and limited complexity, thereby\ndiffering significantly from the conditions artificial agents are exposed to.\nIn more natural settings, sequential information may become progressively\navailable over time and access to previous experience may be restricted. In\nthis paper, we propose a dual-memory self-organizing architecture for lifelong\nlearning scenarios. The architecture comprises two growing recurrent networks\nwith the complementary tasks of learning object instances (episodic memory) and\ncategories (semantic memory). Both growing networks can expand in response to\nnovel sensory experience: the episodic memory learns fine-grained\nspatiotemporal representations of object instances in an unsupervised fashion\nwhile the semantic memory uses task-relevant signals to regulate structural\nplasticity levels and develop more compact representations from episodic\nexperience. For the consolidation of knowledge in the absence of external\nsensory input, the episodic memory periodically replays trajectories of neural\nreactivations. We evaluate the proposed model on the CORe50 benchmark dataset\nfor continuous object recognition, showing that we significantly outperform\ncurrent methods of lifelong learning in three different incremental learning\nscenarios","url_abs":"http://arxiv.org/abs/1805.10966v4","url_pdf":"http://arxiv.org/pdf/1805.10966v4.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":"lifelong-learning-of-spatiotemporal","repo_url":"https://github.com/giparisi/GDM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"continuous-object-recognition","task_name":"Continuous Object Recognition"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"lifelong-learning","task_name":"Lifelong learning"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.10966","atlas_url":"https://app.syntology.ai/?focus=1805.10966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.10966"}},"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/giparisi/GDM","reach":null}],"summary":{"ran_draft_wrong":2,"ran_honours":2},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"7810270ec2cc4a7a","entry":"import_network","repo":"giparisi/GDM","repo_kind":"official","path":"gtls.py","file_url":"https://github.com/giparisi/GDM/blob/HEAD/gtls.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7810270ec2cc4a7a"}},{"code_sha256_prefix":"7bcff111584386fc","entry":"load_file","repo":"giparisi/GDM","repo_kind":"official","path":"gtls.py","file_url":"https://github.com/giparisi/GDM/blob/HEAD/gtls.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7bcff111584386fc"}},{"code_sha256_prefix":"0aa9023de3483559","entry":"normalize_data","repo":"giparisi/GDM","repo_kind":"official","path":"gtls.py","file_url":"https://github.com/giparisi/GDM/blob/HEAD/gtls.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0aa9023de3483559"}},{"code_sha256_prefix":"7855297fc6240100","entry":"replay_samples","repo":"giparisi/GDM","repo_kind":"official","path":"gdm_demo.py","file_url":"https://github.com/giparisi/GDM/blob/HEAD/gdm_demo.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7855297fc6240100"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}