{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:J2F5MJL4A2G57INJXF3IX5AA2N","short_pith_number":"pith:J2F5MJL4","schema_version":"1.0","canonical_sha256":"4e8bd6257c068ddfa1a9b9768bf400d3559f4b34dbc3d7ad2317ee40ee4ac625","source":{"kind":"arxiv","id":"1811.03378","version":1},"attestation_state":"computed","paper":{"title":"Activation Functions: Comparison of trends in Practice and Research for Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Anthony Gachagan, Chigozie Nwankpa, Stephen Marshall, Winifred Ijomah","submitted_at":"2018-11-08T12:28:43Z","abstract_excerpt":"Deep neural networks have been successfully used in diverse emerging domains to solve real world complex problems with may more deep learning(DL) architectures, being developed to date. To achieve these state-of-the-art performances, the DL architectures use activation functions (AFs), to perform diverse computations between the hidden layers and the output layers of any given DL architecture. This paper presents a survey on the existing AFs used in deep learning applications and highlights the recent trends in the use of the activation functions for deep learning applications. The novelty of "},"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":"1811.03378","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-08T12:28:43Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7a211e532b1e50468bb63827f8274bdc204472aabc837dc3f55e13e28983b852","abstract_canon_sha256":"e1015482f8d15bbe63b8416e95ad0da1fa41c984ab878e54a1111825d188c64f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:16.839516Z","signature_b64":"Ebe7mkj0L3pnO6Niiy1Y8KWIk9a4ubJqIbnUX01GgQrtdVPyjOt0YY3pQL596XN7Srr+bAAwMScqOuVSwcL7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e8bd6257c068ddfa1a9b9768bf400d3559f4b34dbc3d7ad2317ee40ee4ac625","last_reissued_at":"2026-05-18T00:01:16.839057Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:16.839057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Activation Functions: Comparison of trends in Practice and Research for Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Anthony Gachagan, Chigozie Nwankpa, Stephen Marshall, Winifred Ijomah","submitted_at":"2018-11-08T12:28:43Z","abstract_excerpt":"Deep neural networks have been successfully used in diverse emerging domains to solve real world complex problems with may more deep learning(DL) architectures, being developed to date. To achieve these state-of-the-art performances, the DL architectures use activation functions (AFs), to perform diverse computations between the hidden layers and the output layers of any given DL architecture. This paper presents a survey on the existing AFs used in deep learning applications and highlights the recent trends in the use of the activation functions for deep learning applications. The novelty of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03378","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":"1811.03378","created_at":"2026-05-18T00:01:16.839123+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.03378v1","created_at":"2026-05-18T00:01:16.839123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03378","created_at":"2026-05-18T00:01:16.839123+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2F5MJL4A2G5","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2F5MJL4A2G57INJ","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2F5MJL4","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.07567","citing_title":"SurfDesign: Effective Protein Design on Molecular Surfaces","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08196","citing_title":"Survey on Disaster Management Datasets for Remote Sensing Based Emergency Applications","ref_index":132,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J2F5MJL4A2G57INJXF3IX5AA2N","json":"https://pith.science/pith/J2F5MJL4A2G57INJXF3IX5AA2N.json","graph_json":"https://pith.science/api/pith-number/J2F5MJL4A2G57INJXF3IX5AA2N/graph.json","events_json":"https://pith.science/api/pith-number/J2F5MJL4A2G57INJXF3IX5AA2N/events.json","paper":"https://pith.science/paper/J2F5MJL4"},"agent_actions":{"view_html":"https://pith.science/pith/J2F5MJL4A2G57INJXF3IX5AA2N","download_json":"https://pith.science/pith/J2F5MJL4A2G57INJXF3IX5AA2N.json","view_paper":"https://pith.science/paper/J2F5MJL4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.03378&json=true","fetch_graph":"https://pith.science/api/pith-number/J2F5MJL4A2G57INJXF3IX5AA2N/graph.json","fetch_events":"https://pith.science/api/pith-number/J2F5MJL4A2G57INJXF3IX5AA2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2F5MJL4A2G57INJXF3IX5AA2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2F5MJL4A2G57INJXF3IX5AA2N/action/storage_attestation","attest_author":"https://pith.science/pith/J2F5MJL4A2G57INJXF3IX5AA2N/action/author_attestation","sign_citation":"https://pith.science/pith/J2F5MJL4A2G57INJXF3IX5AA2N/action/citation_signature","submit_replication":"https://pith.science/pith/J2F5MJL4A2G57INJXF3IX5AA2N/action/replication_record"}},"created_at":"2026-05-18T00:01:16.839123+00:00","updated_at":"2026-05-18T00:01:16.839123+00:00"}