{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:O3AX5QMWSKYLJ6ZPBGBOJP2MON","short_pith_number":"pith:O3AX5QMW","schema_version":"1.0","canonical_sha256":"76c17ec19692b0b4fb2f0982e4bf4c7377d05f5f837dec1d29ae5b49a17c1aea","source":{"kind":"arxiv","id":"1610.06160","version":1},"attestation_state":"computed","paper":{"title":"Streaming Normalization: Towards Simpler and More Biologically-plausible Normalizations for Online and Recurrent Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Kenji Kawaguchi, Qianli Liao, Tomaso Poggio","submitted_at":"2016-10-19T19:34:48Z","abstract_excerpt":"We systematically explored a spectrum of normalization algorithms related to Batch Normalization (BN) and propose a generalized formulation that simultaneously solves two major limitations of BN: (1) online learning and (2) recurrent learning. Our proposal is simpler and more biologically-plausible. Unlike previous approaches, our technique can be applied out of the box to all learning scenarios (e.g., online learning, batch learning, fully-connected, convolutional, feedforward, recurrent and mixed --- recurrent and convolutional) and compare favorably with existing approaches. We also propose"},"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":"1610.06160","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-19T19:34:48Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"a8200e77907a8bc255fe3bcaf755bdabbe56f83d8ca379eb927808438b49ca79","abstract_canon_sha256":"c2c4dcbaa50f9db6e4695d1cc2400d243fefd4dfadaecf3d07ee063055fd5e41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:01:49.832705Z","signature_b64":"/mdnTiz+4+Nqi9ODm8HFZ4fX0NCsCxLCULg40AUZDMqC80QU8RwnR0Gtr1EeNVQ+iBVhOlow6ygsSi7hbPUIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76c17ec19692b0b4fb2f0982e4bf4c7377d05f5f837dec1d29ae5b49a17c1aea","last_reissued_at":"2026-05-18T01:01:49.832107Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:01:49.832107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming Normalization: Towards Simpler and More Biologically-plausible Normalizations for Online and Recurrent Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Kenji Kawaguchi, Qianli Liao, Tomaso Poggio","submitted_at":"2016-10-19T19:34:48Z","abstract_excerpt":"We systematically explored a spectrum of normalization algorithms related to Batch Normalization (BN) and propose a generalized formulation that simultaneously solves two major limitations of BN: (1) online learning and (2) recurrent learning. Our proposal is simpler and more biologically-plausible. Unlike previous approaches, our technique can be applied out of the box to all learning scenarios (e.g., online learning, batch learning, fully-connected, convolutional, feedforward, recurrent and mixed --- recurrent and convolutional) and compare favorably with existing approaches. We also propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.06160","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":"1610.06160","created_at":"2026-05-18T01:01:49.832187+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.06160v1","created_at":"2026-05-18T01:01:49.832187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.06160","created_at":"2026-05-18T01:01:49.832187+00:00"},{"alias_kind":"pith_short_12","alias_value":"O3AX5QMWSKYL","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"O3AX5QMWSKYLJ6ZP","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"O3AX5QMW","created_at":"2026-05-18T12:30:36.002864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.10473","citing_title":"Switchable Normalization for Learning-to-Normalize Deep Representation","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O3AX5QMWSKYLJ6ZPBGBOJP2MON","json":"https://pith.science/pith/O3AX5QMWSKYLJ6ZPBGBOJP2MON.json","graph_json":"https://pith.science/api/pith-number/O3AX5QMWSKYLJ6ZPBGBOJP2MON/graph.json","events_json":"https://pith.science/api/pith-number/O3AX5QMWSKYLJ6ZPBGBOJP2MON/events.json","paper":"https://pith.science/paper/O3AX5QMW"},"agent_actions":{"view_html":"https://pith.science/pith/O3AX5QMWSKYLJ6ZPBGBOJP2MON","download_json":"https://pith.science/pith/O3AX5QMWSKYLJ6ZPBGBOJP2MON.json","view_paper":"https://pith.science/paper/O3AX5QMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.06160&json=true","fetch_graph":"https://pith.science/api/pith-number/O3AX5QMWSKYLJ6ZPBGBOJP2MON/graph.json","fetch_events":"https://pith.science/api/pith-number/O3AX5QMWSKYLJ6ZPBGBOJP2MON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O3AX5QMWSKYLJ6ZPBGBOJP2MON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O3AX5QMWSKYLJ6ZPBGBOJP2MON/action/storage_attestation","attest_author":"https://pith.science/pith/O3AX5QMWSKYLJ6ZPBGBOJP2MON/action/author_attestation","sign_citation":"https://pith.science/pith/O3AX5QMWSKYLJ6ZPBGBOJP2MON/action/citation_signature","submit_replication":"https://pith.science/pith/O3AX5QMWSKYLJ6ZPBGBOJP2MON/action/replication_record"}},"created_at":"2026-05-18T01:01:49.832187+00:00","updated_at":"2026-05-18T01:01:49.832187+00:00"}