{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ERJ7U7ZXWRUUQ3M5ILRHCFKZ2C","short_pith_number":"pith:ERJ7U7ZX","schema_version":"1.0","canonical_sha256":"2453fa7f37b469486d9d42e2711559d0a0ebd0982f2f96e84ccc368fe4d932dd","source":{"kind":"arxiv","id":"1710.10368","version":2},"attestation_state":"computed","paper":{"title":"Deep Generative Dual Memory Network for Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Nitin Kamra, Umang Gupta, Yan Liu","submitted_at":"2017-10-28T01:45:43Z","abstract_excerpt":"Despite advances in deep learning, neural networks can only learn multiple tasks when trained on them jointly. When tasks arrive sequentially, they lose performance on previously learnt tasks. This phenomenon called catastrophic forgetting is a fundamental challenge to overcome before neural networks can learn continually from incoming data. In this work, we derive inspiration from human memory to develop an architecture capable of learning continuously from sequentially incoming tasks, while averting catastrophic forgetting. Specifically, our contributions are: (i) a dual memory architecture "},"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":"1710.10368","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-28T01:45:43Z","cross_cats_sorted":[],"title_canon_sha256":"01609a8fe1a9c992656fb9b8676121e7d99f3240b07381fa2ce009e8a81219c4","abstract_canon_sha256":"0318e3b4cd3671bfc2de6ea233de861a443e0d255f53f8b139d14cd8be4f5309"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:54.341986Z","signature_b64":"5QPWdHNBPYZNDooYHMXt2pWbCnZO3WBd0GLx4aAnMOaY+enraT8D8SZSKXY1nPnB1C2bYT3Jp3qMguylfkAMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2453fa7f37b469486d9d42e2711559d0a0ebd0982f2f96e84ccc368fe4d932dd","last_reissued_at":"2026-05-18T00:14:54.341165Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:54.341165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Generative Dual Memory Network for Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Nitin Kamra, Umang Gupta, Yan Liu","submitted_at":"2017-10-28T01:45:43Z","abstract_excerpt":"Despite advances in deep learning, neural networks can only learn multiple tasks when trained on them jointly. When tasks arrive sequentially, they lose performance on previously learnt tasks. This phenomenon called catastrophic forgetting is a fundamental challenge to overcome before neural networks can learn continually from incoming data. In this work, we derive inspiration from human memory to develop an architecture capable of learning continuously from sequentially incoming tasks, while averting catastrophic forgetting. Specifically, our contributions are: (i) a dual memory architecture "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10368","kind":"arxiv","version":2},"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":"1710.10368","created_at":"2026-05-18T00:14:54.341287+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.10368v2","created_at":"2026-05-18T00:14:54.341287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10368","created_at":"2026-05-18T00:14:54.341287+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERJ7U7ZXWRUU","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERJ7U7ZXWRUUQ3M5","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERJ7U7ZX","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.02788","citing_title":"Incremental Concept Learning via Online Generative Memory Recall","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERJ7U7ZXWRUUQ3M5ILRHCFKZ2C","json":"https://pith.science/pith/ERJ7U7ZXWRUUQ3M5ILRHCFKZ2C.json","graph_json":"https://pith.science/api/pith-number/ERJ7U7ZXWRUUQ3M5ILRHCFKZ2C/graph.json","events_json":"https://pith.science/api/pith-number/ERJ7U7ZXWRUUQ3M5ILRHCFKZ2C/events.json","paper":"https://pith.science/paper/ERJ7U7ZX"},"agent_actions":{"view_html":"https://pith.science/pith/ERJ7U7ZXWRUUQ3M5ILRHCFKZ2C","download_json":"https://pith.science/pith/ERJ7U7ZXWRUUQ3M5ILRHCFKZ2C.json","view_paper":"https://pith.science/paper/ERJ7U7ZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.10368&json=true","fetch_graph":"https://pith.science/api/pith-number/ERJ7U7ZXWRUUQ3M5ILRHCFKZ2C/graph.json","fetch_events":"https://pith.science/api/pith-number/ERJ7U7ZXWRUUQ3M5ILRHCFKZ2C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERJ7U7ZXWRUUQ3M5ILRHCFKZ2C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERJ7U7ZXWRUUQ3M5ILRHCFKZ2C/action/storage_attestation","attest_author":"https://pith.science/pith/ERJ7U7ZXWRUUQ3M5ILRHCFKZ2C/action/author_attestation","sign_citation":"https://pith.science/pith/ERJ7U7ZXWRUUQ3M5ILRHCFKZ2C/action/citation_signature","submit_replication":"https://pith.science/pith/ERJ7U7ZXWRUUQ3M5ILRHCFKZ2C/action/replication_record"}},"created_at":"2026-05-18T00:14:54.341287+00:00","updated_at":"2026-05-18T00:14:54.341287+00:00"}