{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:YENAO7NEG2AXPPRH42GEWOPR6Y","short_pith_number":"pith:YENAO7NE","schema_version":"1.0","canonical_sha256":"c11a077da4368177be27e68c4b39f1f60ffb93f7ae3e1716a8f7168eff506f8a","source":{"kind":"arxiv","id":"1606.02355","version":1},"attestation_state":"computed","paper":{"title":"Active Long Term Memory Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew M. Saxe, Bosco S. Tjan, Jiaping Zhao, Laurent Itti, Tommaso Furlanello","submitted_at":"2016-06-07T23:43:42Z","abstract_excerpt":"Continual Learning in artificial neural networks suffers from interference and forgetting when different tasks are learned sequentially. This paper introduces the Active Long Term Memory Networks (A-LTM), a model of sequential multi-task deep learning that is able to maintain previously learned association between sensory input and behavioral output while acquiring knew knowledge. A-LTM exploits the non-convex nature of deep neural networks and actively maintains knowledge of previously learned, inactive tasks using a distillation loss. Distortions of the learned input-output map are penalized"},"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":"1606.02355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-06-07T23:43:42Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fabf267e23a29f0c902b86b6c23716226776143b47a5113203aaec67a5501f1a","abstract_canon_sha256":"147a1e77297f65ecda2dcfd3d90055c120579acaebe74b393766030f4ac475a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:41.532444Z","signature_b64":"7zR3qdKg06T/gyM+XuQALMEC/Fffqf8CFQqqVVluvF4oQO5AES9bSxBTD2NfFbb7NdzIT7oaruvXhFVZIfO0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c11a077da4368177be27e68c4b39f1f60ffb93f7ae3e1716a8f7168eff506f8a","last_reissued_at":"2026-05-18T01:12:41.532083Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:41.532083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Long Term Memory Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew M. Saxe, Bosco S. Tjan, Jiaping Zhao, Laurent Itti, Tommaso Furlanello","submitted_at":"2016-06-07T23:43:42Z","abstract_excerpt":"Continual Learning in artificial neural networks suffers from interference and forgetting when different tasks are learned sequentially. This paper introduces the Active Long Term Memory Networks (A-LTM), a model of sequential multi-task deep learning that is able to maintain previously learned association between sensory input and behavioral output while acquiring knew knowledge. A-LTM exploits the non-convex nature of deep neural networks and actively maintains knowledge of previously learned, inactive tasks using a distillation loss. Distortions of the learned input-output map are penalized"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.02355","kind":"arxiv","version":1},"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":"1606.02355","created_at":"2026-05-18T01:12:41.532139+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.02355v1","created_at":"2026-05-18T01:12:41.532139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.02355","created_at":"2026-05-18T01:12:41.532139+00:00"},{"alias_kind":"pith_short_12","alias_value":"YENAO7NEG2AX","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"YENAO7NEG2AXPPRH","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"YENAO7NE","created_at":"2026-05-18T12:30:53.716459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.07844","citing_title":"Growing a Brain: Fine-Tuning by Increasing Model Capacity","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YENAO7NEG2AXPPRH42GEWOPR6Y","json":"https://pith.science/pith/YENAO7NEG2AXPPRH42GEWOPR6Y.json","graph_json":"https://pith.science/api/pith-number/YENAO7NEG2AXPPRH42GEWOPR6Y/graph.json","events_json":"https://pith.science/api/pith-number/YENAO7NEG2AXPPRH42GEWOPR6Y/events.json","paper":"https://pith.science/paper/YENAO7NE"},"agent_actions":{"view_html":"https://pith.science/pith/YENAO7NEG2AXPPRH42GEWOPR6Y","download_json":"https://pith.science/pith/YENAO7NEG2AXPPRH42GEWOPR6Y.json","view_paper":"https://pith.science/paper/YENAO7NE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.02355&json=true","fetch_graph":"https://pith.science/api/pith-number/YENAO7NEG2AXPPRH42GEWOPR6Y/graph.json","fetch_events":"https://pith.science/api/pith-number/YENAO7NEG2AXPPRH42GEWOPR6Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YENAO7NEG2AXPPRH42GEWOPR6Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YENAO7NEG2AXPPRH42GEWOPR6Y/action/storage_attestation","attest_author":"https://pith.science/pith/YENAO7NEG2AXPPRH42GEWOPR6Y/action/author_attestation","sign_citation":"https://pith.science/pith/YENAO7NEG2AXPPRH42GEWOPR6Y/action/citation_signature","submit_replication":"https://pith.science/pith/YENAO7NEG2AXPPRH42GEWOPR6Y/action/replication_record"}},"created_at":"2026-05-18T01:12:41.532139+00:00","updated_at":"2026-05-18T01:12:41.532139+00:00"}