{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:JN5ZRI3YBEZL5KNHXPAWHX2Y4B","short_pith_number":"pith:JN5ZRI3Y","schema_version":"1.0","canonical_sha256":"4b7b98a3780932bea9a7bbc163df58e07b5fcfde4bbf9cd26107c354d02a9a9b","source":{"kind":"arxiv","id":"1512.01400","version":1},"attestation_state":"computed","paper":{"title":"Max-Pooling Dropout for Regularization of Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Haibing Wu, Xiaodong Gu","submitted_at":"2015-12-04T13:18:37Z","abstract_excerpt":"Recently, dropout has seen increasing use in deep learning. For deep convolutional neural networks, dropout is known to work well in fully-connected layers. However, its effect in pooling layers is still not clear. This paper demonstrates that max-pooling dropout is equivalent to randomly picking activation based on a multinomial distribution at training time. In light of this insight, we advocate employing our proposed probabilistic weighted pooling, instead of commonly used max-pooling, to act as model averaging at test time. Empirical evidence validates the superiority of probabilistic weig"},"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":"1512.01400","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-04T13:18:37Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"9f1bb432a2c223e55756e15e6e479749deed7f1f6f90614a2604afe104273ee6","abstract_canon_sha256":"572833c0b53afe84dba6224d3391fbb0c7eedb9ab2fb1353747644d0eec612c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:25:17.012839Z","signature_b64":"CjgE5bz2sZ8TpNkwrjzjL/vCwjNwClzCuZ+JiSRAyJ4VppTSfZs8D69xIlYIB2C7XHPFgtkfHDzXSJTB5KitDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b7b98a3780932bea9a7bbc163df58e07b5fcfde4bbf9cd26107c354d02a9a9b","last_reissued_at":"2026-05-18T01:25:17.012140Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:25:17.012140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Max-Pooling Dropout for Regularization of Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Haibing Wu, Xiaodong Gu","submitted_at":"2015-12-04T13:18:37Z","abstract_excerpt":"Recently, dropout has seen increasing use in deep learning. For deep convolutional neural networks, dropout is known to work well in fully-connected layers. However, its effect in pooling layers is still not clear. This paper demonstrates that max-pooling dropout is equivalent to randomly picking activation based on a multinomial distribution at training time. In light of this insight, we advocate employing our proposed probabilistic weighted pooling, instead of commonly used max-pooling, to act as model averaging at test time. Empirical evidence validates the superiority of probabilistic weig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.01400","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":"1512.01400","created_at":"2026-05-18T01:25:17.012243+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.01400v1","created_at":"2026-05-18T01:25:17.012243+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.01400","created_at":"2026-05-18T01:25:17.012243+00:00"},{"alias_kind":"pith_short_12","alias_value":"JN5ZRI3YBEZL","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_16","alias_value":"JN5ZRI3YBEZL5KNH","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_8","alias_value":"JN5ZRI3Y","created_at":"2026-05-18T12:29:27.538025+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/JN5ZRI3YBEZL5KNHXPAWHX2Y4B","json":"https://pith.science/pith/JN5ZRI3YBEZL5KNHXPAWHX2Y4B.json","graph_json":"https://pith.science/api/pith-number/JN5ZRI3YBEZL5KNHXPAWHX2Y4B/graph.json","events_json":"https://pith.science/api/pith-number/JN5ZRI3YBEZL5KNHXPAWHX2Y4B/events.json","paper":"https://pith.science/paper/JN5ZRI3Y"},"agent_actions":{"view_html":"https://pith.science/pith/JN5ZRI3YBEZL5KNHXPAWHX2Y4B","download_json":"https://pith.science/pith/JN5ZRI3YBEZL5KNHXPAWHX2Y4B.json","view_paper":"https://pith.science/paper/JN5ZRI3Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.01400&json=true","fetch_graph":"https://pith.science/api/pith-number/JN5ZRI3YBEZL5KNHXPAWHX2Y4B/graph.json","fetch_events":"https://pith.science/api/pith-number/JN5ZRI3YBEZL5KNHXPAWHX2Y4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JN5ZRI3YBEZL5KNHXPAWHX2Y4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JN5ZRI3YBEZL5KNHXPAWHX2Y4B/action/storage_attestation","attest_author":"https://pith.science/pith/JN5ZRI3YBEZL5KNHXPAWHX2Y4B/action/author_attestation","sign_citation":"https://pith.science/pith/JN5ZRI3YBEZL5KNHXPAWHX2Y4B/action/citation_signature","submit_replication":"https://pith.science/pith/JN5ZRI3YBEZL5KNHXPAWHX2Y4B/action/replication_record"}},"created_at":"2026-05-18T01:25:17.012243+00:00","updated_at":"2026-05-18T01:25:17.012243+00:00"}