{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:H6HEBQBBWLDDV2S63PTBFUU6YB","short_pith_number":"pith:H6HEBQBB","schema_version":"1.0","canonical_sha256":"3f8e40c021b2c63aea5edbe612d29ec06b5f4d2640cb7b226dfa5ad495cc2008","source":{"kind":"arxiv","id":"1803.10560","version":1},"attestation_state":"computed","paper":{"title":"Normalization of Neural Networks using Analytic Variance Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Shekhovtsov, Boris Flach","submitted_at":"2018-03-28T12:37:27Z","abstract_excerpt":"We address the problem of estimating statistics of hidden units in a neural network using a method of analytic moment propagation. These statistics are useful for approximate whitening of the inputs in front of saturating non-linearities such as a sigmoid function. This is important for initialization of training and for reducing the accumulated scale and bias dependencies (compensating covariate shift), which presumably eases the learning. In batch normalization, which is currently a very widely applied technique, sample estimates of statistics of hidden units over a batch are used. The propo"},"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":"1803.10560","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-28T12:37:27Z","cross_cats_sorted":["cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"cc218178f143f8ede3dc1ccab6f69bef0c616d4618ab3d3fbddda41baddd82cd","abstract_canon_sha256":"8d1bec41cf45194ca7c7b8ebbab652589f70efe3aa23ce9b8822c0a543964a92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:54.916489Z","signature_b64":"HUFoGieL4liyPAgQw6ykozC/bD9UTFr9CY5/SnOW+WVE2PjwThdXzBvAL3Uy9cft5paiyuWllPm8NxOYd+OqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f8e40c021b2c63aea5edbe612d29ec06b5f4d2640cb7b226dfa5ad495cc2008","last_reissued_at":"2026-05-18T00:19:54.915757Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:54.915757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Normalization of Neural Networks using Analytic Variance Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Shekhovtsov, Boris Flach","submitted_at":"2018-03-28T12:37:27Z","abstract_excerpt":"We address the problem of estimating statistics of hidden units in a neural network using a method of analytic moment propagation. These statistics are useful for approximate whitening of the inputs in front of saturating non-linearities such as a sigmoid function. This is important for initialization of training and for reducing the accumulated scale and bias dependencies (compensating covariate shift), which presumably eases the learning. In batch normalization, which is currently a very widely applied technique, sample estimates of statistics of hidden units over a batch are used. The propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10560","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":"1803.10560","created_at":"2026-05-18T00:19:54.915875+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.10560v1","created_at":"2026-05-18T00:19:54.915875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10560","created_at":"2026-05-18T00:19:54.915875+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6HEBQBBWLDD","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6HEBQBBWLDDV2S6","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6HEBQBB","created_at":"2026-05-18T12:32:28.185984+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/H6HEBQBBWLDDV2S63PTBFUU6YB","json":"https://pith.science/pith/H6HEBQBBWLDDV2S63PTBFUU6YB.json","graph_json":"https://pith.science/api/pith-number/H6HEBQBBWLDDV2S63PTBFUU6YB/graph.json","events_json":"https://pith.science/api/pith-number/H6HEBQBBWLDDV2S63PTBFUU6YB/events.json","paper":"https://pith.science/paper/H6HEBQBB"},"agent_actions":{"view_html":"https://pith.science/pith/H6HEBQBBWLDDV2S63PTBFUU6YB","download_json":"https://pith.science/pith/H6HEBQBBWLDDV2S63PTBFUU6YB.json","view_paper":"https://pith.science/paper/H6HEBQBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.10560&json=true","fetch_graph":"https://pith.science/api/pith-number/H6HEBQBBWLDDV2S63PTBFUU6YB/graph.json","fetch_events":"https://pith.science/api/pith-number/H6HEBQBBWLDDV2S63PTBFUU6YB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6HEBQBBWLDDV2S63PTBFUU6YB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6HEBQBBWLDDV2S63PTBFUU6YB/action/storage_attestation","attest_author":"https://pith.science/pith/H6HEBQBBWLDDV2S63PTBFUU6YB/action/author_attestation","sign_citation":"https://pith.science/pith/H6HEBQBBWLDDV2S63PTBFUU6YB/action/citation_signature","submit_replication":"https://pith.science/pith/H6HEBQBBWLDDV2S63PTBFUU6YB/action/replication_record"}},"created_at":"2026-05-18T00:19:54.915875+00:00","updated_at":"2026-05-18T00:19:54.915875+00:00"}