{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:3IYHH54E7MGJB3FTAXIEQOO7FY","short_pith_number":"pith:3IYHH54E","schema_version":"1.0","canonical_sha256":"da3073f784fb0c90ecb305d04839df2e0ea999f4d1f9c34994edba6e889d3508","source":{"kind":"arxiv","id":"1311.1780","version":7},"attestation_state":"computed","paper":{"title":"Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Caglar Gulcehre, Kyunghyun Cho, Razvan Pascanu, Yoshua Bengio","submitted_at":"2013-11-07T18:30:37Z","abstract_excerpt":"In this paper we propose and investigate a novel nonlinear unit, called $L_p$ unit, for deep neural networks. The proposed $L_p$ unit receives signals from several projections of a subset of units in the layer below and computes a normalized $L_p$ norm. We notice two interesting interpretations of the $L_p$ unit. First, the proposed unit can be understood as a generalization of a number of conventional pooling operators such as average, root-mean-square and max pooling widely used in, for instance, convolutional neural networks (CNN), HMAX models and neocognitrons. Furthermore, the $L_p$ unit "},"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":"1311.1780","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2013-11-07T18:30:37Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"aac907c5ec1bf077142934130e352bcdf9f277bc05da48107513416b1e0e1ecf","abstract_canon_sha256":"d4ec47c1acd5cf08be7ee2da3adc232a0485862dc41743774df0062ea435ec4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:43:52.335436Z","signature_b64":"ig0m8PKLtYkLL75R/xnqFebNc7oR+YYEoyGhmy7ERSVf5k4yzoLJG4OY8+9r5mus8iWBXQUaTv38omxAcchoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da3073f784fb0c90ecb305d04839df2e0ea999f4d1f9c34994edba6e889d3508","last_reissued_at":"2026-05-18T02:43:52.335002Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:43:52.335002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Caglar Gulcehre, Kyunghyun Cho, Razvan Pascanu, Yoshua Bengio","submitted_at":"2013-11-07T18:30:37Z","abstract_excerpt":"In this paper we propose and investigate a novel nonlinear unit, called $L_p$ unit, for deep neural networks. The proposed $L_p$ unit receives signals from several projections of a subset of units in the layer below and computes a normalized $L_p$ norm. We notice two interesting interpretations of the $L_p$ unit. First, the proposed unit can be understood as a generalization of a number of conventional pooling operators such as average, root-mean-square and max pooling widely used in, for instance, convolutional neural networks (CNN), HMAX models and neocognitrons. Furthermore, the $L_p$ unit "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.1780","kind":"arxiv","version":7},"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":"1311.1780","created_at":"2026-05-18T02:43:52.335057+00:00"},{"alias_kind":"arxiv_version","alias_value":"1311.1780v7","created_at":"2026-05-18T02:43:52.335057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.1780","created_at":"2026-05-18T02:43:52.335057+00:00"},{"alias_kind":"pith_short_12","alias_value":"3IYHH54E7MGJ","created_at":"2026-05-18T12:27:32.513160+00:00"},{"alias_kind":"pith_short_16","alias_value":"3IYHH54E7MGJB3FT","created_at":"2026-05-18T12:27:32.513160+00:00"},{"alias_kind":"pith_short_8","alias_value":"3IYHH54E","created_at":"2026-05-18T12:27:32.513160+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/3IYHH54E7MGJB3FTAXIEQOO7FY","json":"https://pith.science/pith/3IYHH54E7MGJB3FTAXIEQOO7FY.json","graph_json":"https://pith.science/api/pith-number/3IYHH54E7MGJB3FTAXIEQOO7FY/graph.json","events_json":"https://pith.science/api/pith-number/3IYHH54E7MGJB3FTAXIEQOO7FY/events.json","paper":"https://pith.science/paper/3IYHH54E"},"agent_actions":{"view_html":"https://pith.science/pith/3IYHH54E7MGJB3FTAXIEQOO7FY","download_json":"https://pith.science/pith/3IYHH54E7MGJB3FTAXIEQOO7FY.json","view_paper":"https://pith.science/paper/3IYHH54E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1311.1780&json=true","fetch_graph":"https://pith.science/api/pith-number/3IYHH54E7MGJB3FTAXIEQOO7FY/graph.json","fetch_events":"https://pith.science/api/pith-number/3IYHH54E7MGJB3FTAXIEQOO7FY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3IYHH54E7MGJB3FTAXIEQOO7FY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3IYHH54E7MGJB3FTAXIEQOO7FY/action/storage_attestation","attest_author":"https://pith.science/pith/3IYHH54E7MGJB3FTAXIEQOO7FY/action/author_attestation","sign_citation":"https://pith.science/pith/3IYHH54E7MGJB3FTAXIEQOO7FY/action/citation_signature","submit_replication":"https://pith.science/pith/3IYHH54E7MGJB3FTAXIEQOO7FY/action/replication_record"}},"created_at":"2026-05-18T02:43:52.335057+00:00","updated_at":"2026-05-18T02:43:52.335057+00:00"}