{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:UESVFLJY4JQJ5TJBQXFGJJDS6O","short_pith_number":"pith:UESVFLJY","schema_version":"1.0","canonical_sha256":"a12552ad38e2609ecd2185ca64a472f38e35e7a6d524cec46f70a7817845bddd","source":{"kind":"arxiv","id":"1605.09332","version":4},"attestation_state":"computed","paper":{"title":"Parametric Exponential Linear Unit for Deep 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":"Brahim Chaib-draa, Ludovic Trottier, Philippe Gigu\\`ere","submitted_at":"2016-05-30T17:16:40Z","abstract_excerpt":"Object recognition is an important task for improving the ability of visual systems to perform complex scene understanding. Recently, the Exponential Linear Unit (ELU) has been proposed as a key component for managing bias shift in Convolutional Neural Networks (CNNs), but defines a parameter that must be set by hand. In this paper, we propose learning a parameterization of ELU in order to learn the proper activation shape at each layer in the CNNs. Our results on the MNIST, CIFAR-10/100 and ImageNet datasets using the NiN, Overfeat, All-CNN and ResNet networks indicate that our proposed Param"},"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":"1605.09332","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-30T17:16:40Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"f490f15194067f7bbb9c878f42fe9472dc17d7782f9e811a35ef21fbf5890fce","abstract_canon_sha256":"c280f78770b23416c3f09d30288c0132e85099ecb3c48ad555355dad713f6cbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:18.548899Z","signature_b64":"glQ0fWjM8fE3CKXy+P9VQkFQim4SPBwaLwGOysLxAjmiZ1884grMxQuvgJ1TXPsPqNZRw4T1/EPZXqvVHkK3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a12552ad38e2609ecd2185ca64a472f38e35e7a6d524cec46f70a7817845bddd","last_reissued_at":"2026-05-18T00:26:18.548340Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:18.548340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parametric Exponential Linear Unit for Deep 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":"Brahim Chaib-draa, Ludovic Trottier, Philippe Gigu\\`ere","submitted_at":"2016-05-30T17:16:40Z","abstract_excerpt":"Object recognition is an important task for improving the ability of visual systems to perform complex scene understanding. Recently, the Exponential Linear Unit (ELU) has been proposed as a key component for managing bias shift in Convolutional Neural Networks (CNNs), but defines a parameter that must be set by hand. In this paper, we propose learning a parameterization of ELU in order to learn the proper activation shape at each layer in the CNNs. Our results on the MNIST, CIFAR-10/100 and ImageNet datasets using the NiN, Overfeat, All-CNN and ResNet networks indicate that our proposed Param"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.09332","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":"1605.09332","created_at":"2026-05-18T00:26:18.548438+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.09332v4","created_at":"2026-05-18T00:26:18.548438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.09332","created_at":"2026-05-18T00:26:18.548438+00:00"},{"alias_kind":"pith_short_12","alias_value":"UESVFLJY4JQJ","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_16","alias_value":"UESVFLJY4JQJ5TJB","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_8","alias_value":"UESVFLJY","created_at":"2026-05-18T12:30:46.583412+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/UESVFLJY4JQJ5TJBQXFGJJDS6O","json":"https://pith.science/pith/UESVFLJY4JQJ5TJBQXFGJJDS6O.json","graph_json":"https://pith.science/api/pith-number/UESVFLJY4JQJ5TJBQXFGJJDS6O/graph.json","events_json":"https://pith.science/api/pith-number/UESVFLJY4JQJ5TJBQXFGJJDS6O/events.json","paper":"https://pith.science/paper/UESVFLJY"},"agent_actions":{"view_html":"https://pith.science/pith/UESVFLJY4JQJ5TJBQXFGJJDS6O","download_json":"https://pith.science/pith/UESVFLJY4JQJ5TJBQXFGJJDS6O.json","view_paper":"https://pith.science/paper/UESVFLJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.09332&json=true","fetch_graph":"https://pith.science/api/pith-number/UESVFLJY4JQJ5TJBQXFGJJDS6O/graph.json","fetch_events":"https://pith.science/api/pith-number/UESVFLJY4JQJ5TJBQXFGJJDS6O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UESVFLJY4JQJ5TJBQXFGJJDS6O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UESVFLJY4JQJ5TJBQXFGJJDS6O/action/storage_attestation","attest_author":"https://pith.science/pith/UESVFLJY4JQJ5TJBQXFGJJDS6O/action/author_attestation","sign_citation":"https://pith.science/pith/UESVFLJY4JQJ5TJBQXFGJJDS6O/action/citation_signature","submit_replication":"https://pith.science/pith/UESVFLJY4JQJ5TJBQXFGJJDS6O/action/replication_record"}},"created_at":"2026-05-18T00:26:18.548438+00:00","updated_at":"2026-05-18T00:26:18.548438+00:00"}