{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PV2BNFCFZD5CFM646AC6PPCHZO","short_pith_number":"pith:PV2BNFCF","schema_version":"1.0","canonical_sha256":"7d74169445c8fa22b3dcf005e7bc47cb9387bcc7c6d240d4f8387dcdcf7ef02f","source":{"kind":"arxiv","id":"1806.02892","version":2},"attestation_state":"computed","paper":{"title":"Training Faster by Separating Modes of Variation in Batch-normalized Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mahdi M. Kalayeh, Mubarak Shah","submitted_at":"2018-06-07T20:41:09Z","abstract_excerpt":"Batch Normalization (BN) is essential to effectively train state-of-the-art deep Convolutional Neural Networks (CNN). It normalizes inputs to the layers during training using the statistics of each mini-batch. In this work, we study BN from the viewpoint of Fisher kernels. We show that assuming samples within a mini-batch are from the same probability density function, then BN is identical to the Fisher vector of a Gaussian distribution. That means BN can be explained in terms of kernels that naturally emerge from the probability density function of the underlying data distribution. However, g"},"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":"1806.02892","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-07T20:41:09Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"cbe4782f9645cd6f187add1a3870e825884721ef39ef3f0512e0175c2ae2b5a9","abstract_canon_sha256":"8195446be6cca6c86a0c4cffa249fb98c46fe7c72da0c83cf9553663cf3f68ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:39.526997Z","signature_b64":"HblMe4EdD18benrbL72rQbbworlDFGkvCi0p9KoJ03ii0NN+aY1qtTWVJCB82FqCiH9Tjf99O+npfAHNvGmNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d74169445c8fa22b3dcf005e7bc47cb9387bcc7c6d240d4f8387dcdcf7ef02f","last_reissued_at":"2026-05-18T00:00:39.526442Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:39.526442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Faster by Separating Modes of Variation in Batch-normalized Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mahdi M. Kalayeh, Mubarak Shah","submitted_at":"2018-06-07T20:41:09Z","abstract_excerpt":"Batch Normalization (BN) is essential to effectively train state-of-the-art deep Convolutional Neural Networks (CNN). It normalizes inputs to the layers during training using the statistics of each mini-batch. In this work, we study BN from the viewpoint of Fisher kernels. We show that assuming samples within a mini-batch are from the same probability density function, then BN is identical to the Fisher vector of a Gaussian distribution. That means BN can be explained in terms of kernels that naturally emerge from the probability density function of the underlying data distribution. However, g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02892","kind":"arxiv","version":2},"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":"1806.02892","created_at":"2026-05-18T00:00:39.526536+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.02892v2","created_at":"2026-05-18T00:00:39.526536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02892","created_at":"2026-05-18T00:00:39.526536+00:00"},{"alias_kind":"pith_short_12","alias_value":"PV2BNFCFZD5C","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"PV2BNFCFZD5CFM64","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"PV2BNFCF","created_at":"2026-05-18T12:32:46.962924+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/PV2BNFCFZD5CFM646AC6PPCHZO","json":"https://pith.science/pith/PV2BNFCFZD5CFM646AC6PPCHZO.json","graph_json":"https://pith.science/api/pith-number/PV2BNFCFZD5CFM646AC6PPCHZO/graph.json","events_json":"https://pith.science/api/pith-number/PV2BNFCFZD5CFM646AC6PPCHZO/events.json","paper":"https://pith.science/paper/PV2BNFCF"},"agent_actions":{"view_html":"https://pith.science/pith/PV2BNFCFZD5CFM646AC6PPCHZO","download_json":"https://pith.science/pith/PV2BNFCFZD5CFM646AC6PPCHZO.json","view_paper":"https://pith.science/paper/PV2BNFCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.02892&json=true","fetch_graph":"https://pith.science/api/pith-number/PV2BNFCFZD5CFM646AC6PPCHZO/graph.json","fetch_events":"https://pith.science/api/pith-number/PV2BNFCFZD5CFM646AC6PPCHZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PV2BNFCFZD5CFM646AC6PPCHZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PV2BNFCFZD5CFM646AC6PPCHZO/action/storage_attestation","attest_author":"https://pith.science/pith/PV2BNFCFZD5CFM646AC6PPCHZO/action/author_attestation","sign_citation":"https://pith.science/pith/PV2BNFCFZD5CFM646AC6PPCHZO/action/citation_signature","submit_replication":"https://pith.science/pith/PV2BNFCFZD5CFM646AC6PPCHZO/action/replication_record"}},"created_at":"2026-05-18T00:00:39.526536+00:00","updated_at":"2026-05-18T00:00:39.526536+00:00"}