{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JPOOXK2YQ2TD52NFSQWEPOF7QH","short_pith_number":"pith:JPOOXK2Y","schema_version":"1.0","canonical_sha256":"4bdcebab5886a63ee9a5942c47b8bf81d98682eb52f4627a225fe7af661b0f40","source":{"kind":"arxiv","id":"1802.02950","version":4},"attestation_state":"computed","paper":{"title":"Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew D. Bagdanov, Antonio M. Lopez, Joost Van De Weijer, Luis Herranz, Marc Masana, Xialei Liu","submitted_at":"2018-02-08T16:25:29Z","abstract_excerpt":"In this paper we propose an approach to avoiding catastrophic forgetting in sequential task learning scenarios. Our technique is based on a network reparameterization that approximately diagonalizes the Fisher Information Matrix of the network parameters. This reparameterization takes the form of a factorized rotation of parameter space which, when used in conjunction with Elastic Weight Consolidation (which assumes a diagonal Fisher Information Matrix), leads to significantly better performance on lifelong learning of sequential tasks. Experimental results on the MNIST, CIFAR-100, CUB-200 and"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1802.02950","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-02-08T16:25:29Z","cross_cats_sorted":[],"title_canon_sha256":"2e24813c2d58e3bcf3e002a26dd18f86de1d0bbb1756932e995c23ea65fdf69c","abstract_canon_sha256":"82855ecee59d75782b863b7aa68480ed49f7f88131b76b773b487cb7e6aec6e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:31.036280Z","signature_b64":"Je1QYA32rC1NDXc3MgkFQdb05pgPvQYV4ZDTfvcXuC5SeWe2wdVIulkeM1I8Vz98XY5n/oOh4yk9YYo26RJhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bdcebab5886a63ee9a5942c47b8bf81d98682eb52f4627a225fe7af661b0f40","last_reissued_at":"2026-05-17T23:58:31.035622Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:31.035622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew D. Bagdanov, Antonio M. Lopez, Joost Van De Weijer, Luis Herranz, Marc Masana, Xialei Liu","submitted_at":"2018-02-08T16:25:29Z","abstract_excerpt":"In this paper we propose an approach to avoiding catastrophic forgetting in sequential task learning scenarios. Our technique is based on a network reparameterization that approximately diagonalizes the Fisher Information Matrix of the network parameters. This reparameterization takes the form of a factorized rotation of parameter space which, when used in conjunction with Elastic Weight Consolidation (which assumes a diagonal Fisher Information Matrix), leads to significantly better performance on lifelong learning of sequential tasks. Experimental results on the MNIST, CIFAR-100, CUB-200 and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.02950","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1802.02950","created_at":"2026-05-17T23:58:31.035714+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.02950v4","created_at":"2026-05-17T23:58:31.035714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.02950","created_at":"2026-05-17T23:58:31.035714+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPOOXK2YQ2TD","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPOOXK2YQ2TD52NF","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPOOXK2Y","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JPOOXK2YQ2TD52NFSQWEPOF7QH","json":"https://pith.science/pith/JPOOXK2YQ2TD52NFSQWEPOF7QH.json","graph_json":"https://pith.science/api/pith-number/JPOOXK2YQ2TD52NFSQWEPOF7QH/graph.json","events_json":"https://pith.science/api/pith-number/JPOOXK2YQ2TD52NFSQWEPOF7QH/events.json","paper":"https://pith.science/paper/JPOOXK2Y"},"agent_actions":{"view_html":"https://pith.science/pith/JPOOXK2YQ2TD52NFSQWEPOF7QH","download_json":"https://pith.science/pith/JPOOXK2YQ2TD52NFSQWEPOF7QH.json","view_paper":"https://pith.science/paper/JPOOXK2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.02950&json=true","fetch_graph":"https://pith.science/api/pith-number/JPOOXK2YQ2TD52NFSQWEPOF7QH/graph.json","fetch_events":"https://pith.science/api/pith-number/JPOOXK2YQ2TD52NFSQWEPOF7QH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPOOXK2YQ2TD52NFSQWEPOF7QH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPOOXK2YQ2TD52NFSQWEPOF7QH/action/storage_attestation","attest_author":"https://pith.science/pith/JPOOXK2YQ2TD52NFSQWEPOF7QH/action/author_attestation","sign_citation":"https://pith.science/pith/JPOOXK2YQ2TD52NFSQWEPOF7QH/action/citation_signature","submit_replication":"https://pith.science/pith/JPOOXK2YQ2TD52NFSQWEPOF7QH/action/replication_record"}},"created_at":"2026-05-17T23:58:31.035714+00:00","updated_at":"2026-05-17T23:58:31.035714+00:00"}