{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:P7RS3SJRWCPPFAJYAUKDD7GXJL","short_pith_number":"pith:P7RS3SJR","schema_version":"1.0","canonical_sha256":"7fe32dc931b09ef28138051431fcd74aff2b5def7a6d7b85ff87795d07d4dd66","source":{"kind":"arxiv","id":"1710.02338","version":1},"attestation_state":"computed","paper":{"title":"Projection Based Weight Normalization for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bo Lang, Bo Li, Lei Huang, Xianglong Liu","submitted_at":"2017-10-06T10:24:38Z","abstract_excerpt":"Optimizing deep neural networks (DNNs) often suffers from the ill-conditioned problem. We observe that the scaling-based weight space symmetry property in rectified nonlinear network will cause this negative effect. Therefore, we propose to constrain the incoming weights of each neuron to be unit-norm, which is formulated as an optimization problem over Oblique manifold. A simple yet efficient method referred to as projection based weight normalization (PBWN) is also developed to solve this problem. PBWN executes standard gradient updates, followed by projecting the updated weight back to Obli"},"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":"1710.02338","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-06T10:24:38Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"628f9a2d80d20216378f46c6e8efc9b94e8e749fe75afdf5517970be5dd4d239","abstract_canon_sha256":"b9390d5fd114b6cf21af220830ff589b56a79326e3d21dc421d1c1c98547e045"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:33.690935Z","signature_b64":"KSRRWCPqyY5tbD2uiXPoNrIFUul5jk9ECdU0rXdzLnKi20sw9QHwfIzgNDxT0qU1XIlGVbiTcsIsii5gB8GGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fe32dc931b09ef28138051431fcd74aff2b5def7a6d7b85ff87795d07d4dd66","last_reissued_at":"2026-05-18T00:33:33.690193Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:33.690193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Projection Based Weight Normalization for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bo Lang, Bo Li, Lei Huang, Xianglong Liu","submitted_at":"2017-10-06T10:24:38Z","abstract_excerpt":"Optimizing deep neural networks (DNNs) often suffers from the ill-conditioned problem. We observe that the scaling-based weight space symmetry property in rectified nonlinear network will cause this negative effect. Therefore, we propose to constrain the incoming weights of each neuron to be unit-norm, which is formulated as an optimization problem over Oblique manifold. A simple yet efficient method referred to as projection based weight normalization (PBWN) is also developed to solve this problem. PBWN executes standard gradient updates, followed by projecting the updated weight back to Obli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.02338","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":"1710.02338","created_at":"2026-05-18T00:33:33.690327+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.02338v1","created_at":"2026-05-18T00:33:33.690327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.02338","created_at":"2026-05-18T00:33:33.690327+00:00"},{"alias_kind":"pith_short_12","alias_value":"P7RS3SJRWCPP","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"P7RS3SJRWCPPFAJY","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"P7RS3SJR","created_at":"2026-05-18T12:31:37.085036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04683","citing_title":"Recovering Plasticity of Neural Networks via Soft Weight Rescaling","ref_index":2016,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P7RS3SJRWCPPFAJYAUKDD7GXJL","json":"https://pith.science/pith/P7RS3SJRWCPPFAJYAUKDD7GXJL.json","graph_json":"https://pith.science/api/pith-number/P7RS3SJRWCPPFAJYAUKDD7GXJL/graph.json","events_json":"https://pith.science/api/pith-number/P7RS3SJRWCPPFAJYAUKDD7GXJL/events.json","paper":"https://pith.science/paper/P7RS3SJR"},"agent_actions":{"view_html":"https://pith.science/pith/P7RS3SJRWCPPFAJYAUKDD7GXJL","download_json":"https://pith.science/pith/P7RS3SJRWCPPFAJYAUKDD7GXJL.json","view_paper":"https://pith.science/paper/P7RS3SJR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.02338&json=true","fetch_graph":"https://pith.science/api/pith-number/P7RS3SJRWCPPFAJYAUKDD7GXJL/graph.json","fetch_events":"https://pith.science/api/pith-number/P7RS3SJRWCPPFAJYAUKDD7GXJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P7RS3SJRWCPPFAJYAUKDD7GXJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P7RS3SJRWCPPFAJYAUKDD7GXJL/action/storage_attestation","attest_author":"https://pith.science/pith/P7RS3SJRWCPPFAJYAUKDD7GXJL/action/author_attestation","sign_citation":"https://pith.science/pith/P7RS3SJRWCPPFAJYAUKDD7GXJL/action/citation_signature","submit_replication":"https://pith.science/pith/P7RS3SJRWCPPFAJYAUKDD7GXJL/action/replication_record"}},"created_at":"2026-05-18T00:33:33.690327+00:00","updated_at":"2026-05-18T00:33:33.690327+00:00"}