{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:KHGJO6K4R5JCIGE5VBXMWYZOLV","short_pith_number":"pith:KHGJO6K4","schema_version":"1.0","canonical_sha256":"51cc97795c8f5224189da86ecb632e5d5045e0845773a4f9e5260c28ba9a54c8","source":{"kind":"arxiv","id":"1604.00676","version":1},"attestation_state":"computed","paper":{"title":"Multi-Bias Non-linear Activation in Deep Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyang Li, Wanli Ouyang, Xiaogang Wang","submitted_at":"2016-04-03T19:31:22Z","abstract_excerpt":"As a widely used non-linear activation, Rectified Linear Unit (ReLU) separates noise and signal in a feature map by learning a threshold or bias. However, we argue that the classification of noise and signal not only depends on the magnitude of responses, but also the context of how the feature responses would be used to detect more abstract patterns in higher layers. In order to output multiple response maps with magnitude in different ranges for a particular visual pattern, existing networks employing ReLU and its variants have to learn a large number of redundant filters. In this paper, we "},"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":"1604.00676","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2016-04-03T19:31:22Z","cross_cats_sorted":[],"title_canon_sha256":"e4587d95ded84a66e658bb3653126fd9a214decdf52218679add8ef8732a7011","abstract_canon_sha256":"bd609aa2ad96ba785867a528366cf6c77fb13069d26487ada71f1de9ba36b12a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:48.687993Z","signature_b64":"DD0UjnuD48ZVExtPNBbbJTAr918np9vd6+fGUQly10RERzLsg8PwII6iGCb62oQGDn5pEN+1vYyrTUMlbHnjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51cc97795c8f5224189da86ecb632e5d5045e0845773a4f9e5260c28ba9a54c8","last_reissued_at":"2026-05-18T01:17:48.687420Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:48.687420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Bias Non-linear Activation in Deep Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyang Li, Wanli Ouyang, Xiaogang Wang","submitted_at":"2016-04-03T19:31:22Z","abstract_excerpt":"As a widely used non-linear activation, Rectified Linear Unit (ReLU) separates noise and signal in a feature map by learning a threshold or bias. However, we argue that the classification of noise and signal not only depends on the magnitude of responses, but also the context of how the feature responses would be used to detect more abstract patterns in higher layers. In order to output multiple response maps with magnitude in different ranges for a particular visual pattern, existing networks employing ReLU and its variants have to learn a large number of redundant filters. In this paper, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.00676","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":"1604.00676","created_at":"2026-05-18T01:17:48.687516+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.00676v1","created_at":"2026-05-18T01:17:48.687516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.00676","created_at":"2026-05-18T01:17:48.687516+00:00"},{"alias_kind":"pith_short_12","alias_value":"KHGJO6K4R5JC","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"KHGJO6K4R5JCIGE5","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"KHGJO6K4","created_at":"2026-05-18T12:30:25.849896+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/KHGJO6K4R5JCIGE5VBXMWYZOLV","json":"https://pith.science/pith/KHGJO6K4R5JCIGE5VBXMWYZOLV.json","graph_json":"https://pith.science/api/pith-number/KHGJO6K4R5JCIGE5VBXMWYZOLV/graph.json","events_json":"https://pith.science/api/pith-number/KHGJO6K4R5JCIGE5VBXMWYZOLV/events.json","paper":"https://pith.science/paper/KHGJO6K4"},"agent_actions":{"view_html":"https://pith.science/pith/KHGJO6K4R5JCIGE5VBXMWYZOLV","download_json":"https://pith.science/pith/KHGJO6K4R5JCIGE5VBXMWYZOLV.json","view_paper":"https://pith.science/paper/KHGJO6K4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.00676&json=true","fetch_graph":"https://pith.science/api/pith-number/KHGJO6K4R5JCIGE5VBXMWYZOLV/graph.json","fetch_events":"https://pith.science/api/pith-number/KHGJO6K4R5JCIGE5VBXMWYZOLV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KHGJO6K4R5JCIGE5VBXMWYZOLV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KHGJO6K4R5JCIGE5VBXMWYZOLV/action/storage_attestation","attest_author":"https://pith.science/pith/KHGJO6K4R5JCIGE5VBXMWYZOLV/action/author_attestation","sign_citation":"https://pith.science/pith/KHGJO6K4R5JCIGE5VBXMWYZOLV/action/citation_signature","submit_replication":"https://pith.science/pith/KHGJO6K4R5JCIGE5VBXMWYZOLV/action/replication_record"}},"created_at":"2026-05-18T01:17:48.687516+00:00","updated_at":"2026-05-18T01:17:48.687516+00:00"}