{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6JV6GDAG4WYGABZ7TP47UZMPXP","short_pith_number":"pith:6JV6GDAG","schema_version":"1.0","canonical_sha256":"f26be30c06e5b060073f9bf9fa658fbbd3e9d82ca5bf1fe46138847e5b2a407a","source":{"kind":"arxiv","id":"1906.04734","version":1},"attestation_state":"computed","paper":{"title":"Incremental Classifier Learning Based on PEDCC-Loss and Cosine Distance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Qiuyu Zhu, Xin Ye, Zikuang He","submitted_at":"2019-06-11T04:23:14Z","abstract_excerpt":"The main purpose of incremental learning is to learn new knowledge while not forgetting the knowledge which have been learned before. At present, the main challenge in this area is the catastrophe forgetting, namely the network will lose their performance in the old tasks after training for new tasks. In this paper, we introduce an ensemble method of incremental classifier to alleviate this problem, which is based on the cosine distance between the output feature and the pre-defined center, and can let each task to be preserved in different networks. During training, we make use of PEDCC-Loss "},"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":"1906.04734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T04:23:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"24e46f046ff63821fcf90a304550d65790595f6b8c66b0906c74890af694fede","abstract_canon_sha256":"6a140169694fd0297eb5c949bc8b2a50e7487f8868b7b85fba5353cd0c8e4c16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:32.388679Z","signature_b64":"bd7GiPHsnLBHGqysmmRZI2cDYc8ElfY9+v1Vb2MIhnw/5vdJyHfKi+ct5czniPxURRGxQRmyLFPtxZWlORCxDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f26be30c06e5b060073f9bf9fa658fbbd3e9d82ca5bf1fe46138847e5b2a407a","last_reissued_at":"2026-05-17T23:43:32.388065Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:32.388065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incremental Classifier Learning Based on PEDCC-Loss and Cosine Distance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Qiuyu Zhu, Xin Ye, Zikuang He","submitted_at":"2019-06-11T04:23:14Z","abstract_excerpt":"The main purpose of incremental learning is to learn new knowledge while not forgetting the knowledge which have been learned before. At present, the main challenge in this area is the catastrophe forgetting, namely the network will lose their performance in the old tasks after training for new tasks. In this paper, we introduce an ensemble method of incremental classifier to alleviate this problem, which is based on the cosine distance between the output feature and the pre-defined center, and can let each task to be preserved in different networks. During training, we make use of PEDCC-Loss "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04734","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":"1906.04734","created_at":"2026-05-17T23:43:32.388143+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.04734v1","created_at":"2026-05-17T23:43:32.388143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04734","created_at":"2026-05-17T23:43:32.388143+00:00"},{"alias_kind":"pith_short_12","alias_value":"6JV6GDAG4WYG","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6JV6GDAG4WYGABZ7","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6JV6GDAG","created_at":"2026-05-18T12:33:10.108867+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/6JV6GDAG4WYGABZ7TP47UZMPXP","json":"https://pith.science/pith/6JV6GDAG4WYGABZ7TP47UZMPXP.json","graph_json":"https://pith.science/api/pith-number/6JV6GDAG4WYGABZ7TP47UZMPXP/graph.json","events_json":"https://pith.science/api/pith-number/6JV6GDAG4WYGABZ7TP47UZMPXP/events.json","paper":"https://pith.science/paper/6JV6GDAG"},"agent_actions":{"view_html":"https://pith.science/pith/6JV6GDAG4WYGABZ7TP47UZMPXP","download_json":"https://pith.science/pith/6JV6GDAG4WYGABZ7TP47UZMPXP.json","view_paper":"https://pith.science/paper/6JV6GDAG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.04734&json=true","fetch_graph":"https://pith.science/api/pith-number/6JV6GDAG4WYGABZ7TP47UZMPXP/graph.json","fetch_events":"https://pith.science/api/pith-number/6JV6GDAG4WYGABZ7TP47UZMPXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6JV6GDAG4WYGABZ7TP47UZMPXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6JV6GDAG4WYGABZ7TP47UZMPXP/action/storage_attestation","attest_author":"https://pith.science/pith/6JV6GDAG4WYGABZ7TP47UZMPXP/action/author_attestation","sign_citation":"https://pith.science/pith/6JV6GDAG4WYGABZ7TP47UZMPXP/action/citation_signature","submit_replication":"https://pith.science/pith/6JV6GDAG4WYGABZ7TP47UZMPXP/action/replication_record"}},"created_at":"2026-05-17T23:43:32.388143+00:00","updated_at":"2026-05-17T23:43:32.388143+00:00"}