{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:5ISEVTZDZ63QCALSFEV5QTTSEZ","short_pith_number":"pith:5ISEVTZD","schema_version":"1.0","canonical_sha256":"ea244acf23cfb7010172292bd84e72264f86ec3a3a448515a36ae544a011d7f2","source":{"kind":"arxiv","id":"1702.07790","version":1},"attestation_state":"computed","paper":{"title":"Activation Ensembles for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Diego Klabjan, Mark Harmon","submitted_at":"2017-02-24T22:30:29Z","abstract_excerpt":"Many activation functions have been proposed in the past, but selecting an adequate one requires trial and error. We propose a new methodology of designing activation functions within a neural network at each layer. We call this technique an \"activation ensemble\" because it allows the use of multiple activation functions at each layer. This is done by introducing additional variables, $\\alpha$, at each activation layer of a network to allow for multiple activation functions to be active at each neuron. By design, activations with larger $\\alpha$ values at a neuron is equivalent to having the l"},"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":"1702.07790","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-02-24T22:30:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d7e355796c4372e88435af0c0d9918f6a00a7cfc4df067ab0427e0002ff36e56","abstract_canon_sha256":"70ff3d7736a53a522fd874485da32b8320109ff0a346f98f0fdc7c7a4af34581"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:57.022376Z","signature_b64":"/7iU8YbMEKmNDYWEou5cep6pCWG7f72oUVYk1rIcQIj/yFaJE6EWTPWyaDo2V+XRDOmfxVmNPo2iRzrFAEmXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea244acf23cfb7010172292bd84e72264f86ec3a3a448515a36ae544a011d7f2","last_reissued_at":"2026-05-18T00:49:57.021692Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:57.021692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Activation Ensembles for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Diego Klabjan, Mark Harmon","submitted_at":"2017-02-24T22:30:29Z","abstract_excerpt":"Many activation functions have been proposed in the past, but selecting an adequate one requires trial and error. We propose a new methodology of designing activation functions within a neural network at each layer. We call this technique an \"activation ensemble\" because it allows the use of multiple activation functions at each layer. This is done by introducing additional variables, $\\alpha$, at each activation layer of a network to allow for multiple activation functions to be active at each neuron. By design, activations with larger $\\alpha$ values at a neuron is equivalent to having the l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07790","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":"1702.07790","created_at":"2026-05-18T00:49:57.021791+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.07790v1","created_at":"2026-05-18T00:49:57.021791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07790","created_at":"2026-05-18T00:49:57.021791+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ISEVTZDZ63Q","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ISEVTZDZ63QCALS","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ISEVTZD","created_at":"2026-05-18T12:31:00.734936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05294","citing_title":"Competing nonlinearities, criticality, and order-to-chaos transition in deep networks","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ISEVTZDZ63QCALSFEV5QTTSEZ","json":"https://pith.science/pith/5ISEVTZDZ63QCALSFEV5QTTSEZ.json","graph_json":"https://pith.science/api/pith-number/5ISEVTZDZ63QCALSFEV5QTTSEZ/graph.json","events_json":"https://pith.science/api/pith-number/5ISEVTZDZ63QCALSFEV5QTTSEZ/events.json","paper":"https://pith.science/paper/5ISEVTZD"},"agent_actions":{"view_html":"https://pith.science/pith/5ISEVTZDZ63QCALSFEV5QTTSEZ","download_json":"https://pith.science/pith/5ISEVTZDZ63QCALSFEV5QTTSEZ.json","view_paper":"https://pith.science/paper/5ISEVTZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.07790&json=true","fetch_graph":"https://pith.science/api/pith-number/5ISEVTZDZ63QCALSFEV5QTTSEZ/graph.json","fetch_events":"https://pith.science/api/pith-number/5ISEVTZDZ63QCALSFEV5QTTSEZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ISEVTZDZ63QCALSFEV5QTTSEZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ISEVTZDZ63QCALSFEV5QTTSEZ/action/storage_attestation","attest_author":"https://pith.science/pith/5ISEVTZDZ63QCALSFEV5QTTSEZ/action/author_attestation","sign_citation":"https://pith.science/pith/5ISEVTZDZ63QCALSFEV5QTTSEZ/action/citation_signature","submit_replication":"https://pith.science/pith/5ISEVTZDZ63QCALSFEV5QTTSEZ/action/replication_record"}},"created_at":"2026-05-18T00:49:57.021791+00:00","updated_at":"2026-05-18T00:49:57.021791+00:00"}