{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:RLXFHEDXJP3W3MW6UQJ4BXCITN","short_pith_number":"pith:RLXFHEDX","schema_version":"1.0","canonical_sha256":"8aee5390774bf76db2dea413c0dc489b6620bdd0625981b5545dcd04290ef74b","source":{"kind":"arxiv","id":"1302.4389","version":4},"attestation_state":"computed","paper":{"title":"Maxout Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aaron Courville, David Warde-Farley, Ian J. Goodfellow, Mehdi Mirza, Yoshua Bengio","submitted_at":"2013-02-18T18:59:07Z","abstract_excerpt":"We consider the problem of designing models to leverage a recently introduced approximate model averaging technique called dropout. We define a simple new model called maxout (so named because its output is the max of a set of inputs, and because it is a natural companion to dropout) designed to both facilitate optimization by dropout and improve the accuracy of dropout's fast approximate model averaging technique. We empirically verify that the model successfully accomplishes both of these tasks. We use maxout and dropout to demonstrate state of the art classification performance on four benc"},"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":"1302.4389","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2013-02-18T18:59:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8985a96b60f3febdddad2f129d716e5a12c367f83b2cd83d78dac0721c8605f8","abstract_canon_sha256":"78f918028d584fd7d110b708786faa5595e7f7760e5535db7ca14aa119825fe5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:12:48.303515Z","signature_b64":"hR0djN192OL4VJEAgaKqxKgopqlsKjAJ192pp/Ayu9NgSQ9OXYDX+f32rrKgiQNg/RJXLuOWbgRDNWxL4xyUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aee5390774bf76db2dea413c0dc489b6620bdd0625981b5545dcd04290ef74b","last_reissued_at":"2026-05-18T03:12:48.302711Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:12:48.302711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maxout Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aaron Courville, David Warde-Farley, Ian J. Goodfellow, Mehdi Mirza, Yoshua Bengio","submitted_at":"2013-02-18T18:59:07Z","abstract_excerpt":"We consider the problem of designing models to leverage a recently introduced approximate model averaging technique called dropout. We define a simple new model called maxout (so named because its output is the max of a set of inputs, and because it is a natural companion to dropout) designed to both facilitate optimization by dropout and improve the accuracy of dropout's fast approximate model averaging technique. We empirically verify that the model successfully accomplishes both of these tasks. We use maxout and dropout to demonstrate state of the art classification performance on four benc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1302.4389","kind":"arxiv","version":4},"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":"1302.4389","created_at":"2026-05-18T03:12:48.302846+00:00"},{"alias_kind":"arxiv_version","alias_value":"1302.4389v4","created_at":"2026-05-18T03:12:48.302846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1302.4389","created_at":"2026-05-18T03:12:48.302846+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLXFHEDXJP3W","created_at":"2026-05-18T12:27:59.945178+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLXFHEDXJP3W3MW6","created_at":"2026-05-18T12:27:59.945178+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLXFHEDX","created_at":"2026-05-18T12:27:59.945178+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.08507","citing_title":"Multiple-Identity Image Attacks Against Face-based Identity Verification","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"1907.01686","citing_title":"Machine Reading Comprehension: a Literature Review","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06800","citing_title":"Graph Interpolating Activation Improves Both Natural and Robust Accuracies in Data-Efficient Deep Learning","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"1511.06434","citing_title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"1512.03385","citing_title":"Deep Residual Learning for Image Recognition","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RLXFHEDXJP3W3MW6UQJ4BXCITN","json":"https://pith.science/pith/RLXFHEDXJP3W3MW6UQJ4BXCITN.json","graph_json":"https://pith.science/api/pith-number/RLXFHEDXJP3W3MW6UQJ4BXCITN/graph.json","events_json":"https://pith.science/api/pith-number/RLXFHEDXJP3W3MW6UQJ4BXCITN/events.json","paper":"https://pith.science/paper/RLXFHEDX"},"agent_actions":{"view_html":"https://pith.science/pith/RLXFHEDXJP3W3MW6UQJ4BXCITN","download_json":"https://pith.science/pith/RLXFHEDXJP3W3MW6UQJ4BXCITN.json","view_paper":"https://pith.science/paper/RLXFHEDX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1302.4389&json=true","fetch_graph":"https://pith.science/api/pith-number/RLXFHEDXJP3W3MW6UQJ4BXCITN/graph.json","fetch_events":"https://pith.science/api/pith-number/RLXFHEDXJP3W3MW6UQJ4BXCITN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLXFHEDXJP3W3MW6UQJ4BXCITN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLXFHEDXJP3W3MW6UQJ4BXCITN/action/storage_attestation","attest_author":"https://pith.science/pith/RLXFHEDXJP3W3MW6UQJ4BXCITN/action/author_attestation","sign_citation":"https://pith.science/pith/RLXFHEDXJP3W3MW6UQJ4BXCITN/action/citation_signature","submit_replication":"https://pith.science/pith/RLXFHEDXJP3W3MW6UQJ4BXCITN/action/replication_record"}},"created_at":"2026-05-18T03:12:48.302846+00:00","updated_at":"2026-05-18T03:12:48.302846+00:00"}