{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PQEUK5B4BLJZPQR4654OIP36Z7","short_pith_number":"pith:PQEUK5B4","schema_version":"1.0","canonical_sha256":"7c0945743c0ad397c23cf778e43f7ecfc6d5e2828a6079120783a6d80afd210d","source":{"kind":"arxiv","id":"1807.06302","version":2},"attestation_state":"computed","paper":{"title":"Learning Neuron Non-Linearities with Kernel-Based Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Betti, Dario Zanca, Giuseppe Marra, Marco Gori","submitted_at":"2018-07-17T09:40:56Z","abstract_excerpt":"The effectiveness of deep neural architectures has been widely supported in terms of both experimental and foundational principles. There is also clear evidence that the activation function (e.g. the rectifier and the LSTM units) plays a crucial role in the complexity of learning. Based on this remark, this paper discusses an optimal selection of the neuron non-linearity in a functional framework that is inspired from classic regularization arguments. It is shown that the best activation function is represented by a kernel expansion in the training set, that can be effectively approximated ove"},"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":"1807.06302","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-17T09:40:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cfdc2256dd76d02bc459a981d98b29b4db12e54d538b4256b029dc9aff52e7e8","abstract_canon_sha256":"c33c4f7218aa4ccc8822d575518c3970b8dea69cae40b861230d3f736b82c41a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:02.370715Z","signature_b64":"+53cLzMPPQEb0NmYMX/k8dEwiT3asjZUuIe7i29vclMJ3CQ0XyD4zBPV/xb7OT37YG1lOEVJQX50VjxSLHp2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c0945743c0ad397c23cf778e43f7ecfc6d5e2828a6079120783a6d80afd210d","last_reissued_at":"2026-05-18T00:04:02.370090Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:02.370090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Neuron Non-Linearities with Kernel-Based Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Betti, Dario Zanca, Giuseppe Marra, Marco Gori","submitted_at":"2018-07-17T09:40:56Z","abstract_excerpt":"The effectiveness of deep neural architectures has been widely supported in terms of both experimental and foundational principles. There is also clear evidence that the activation function (e.g. the rectifier and the LSTM units) plays a crucial role in the complexity of learning. Based on this remark, this paper discusses an optimal selection of the neuron non-linearity in a functional framework that is inspired from classic regularization arguments. It is shown that the best activation function is represented by a kernel expansion in the training set, that can be effectively approximated ove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06302","kind":"arxiv","version":2},"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":"1807.06302","created_at":"2026-05-18T00:04:02.370178+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.06302v2","created_at":"2026-05-18T00:04:02.370178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06302","created_at":"2026-05-18T00:04:02.370178+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQEUK5B4BLJZ","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQEUK5B4BLJZPQR4","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQEUK5B4","created_at":"2026-05-18T12:32:46.962924+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/PQEUK5B4BLJZPQR4654OIP36Z7","json":"https://pith.science/pith/PQEUK5B4BLJZPQR4654OIP36Z7.json","graph_json":"https://pith.science/api/pith-number/PQEUK5B4BLJZPQR4654OIP36Z7/graph.json","events_json":"https://pith.science/api/pith-number/PQEUK5B4BLJZPQR4654OIP36Z7/events.json","paper":"https://pith.science/paper/PQEUK5B4"},"agent_actions":{"view_html":"https://pith.science/pith/PQEUK5B4BLJZPQR4654OIP36Z7","download_json":"https://pith.science/pith/PQEUK5B4BLJZPQR4654OIP36Z7.json","view_paper":"https://pith.science/paper/PQEUK5B4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.06302&json=true","fetch_graph":"https://pith.science/api/pith-number/PQEUK5B4BLJZPQR4654OIP36Z7/graph.json","fetch_events":"https://pith.science/api/pith-number/PQEUK5B4BLJZPQR4654OIP36Z7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQEUK5B4BLJZPQR4654OIP36Z7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQEUK5B4BLJZPQR4654OIP36Z7/action/storage_attestation","attest_author":"https://pith.science/pith/PQEUK5B4BLJZPQR4654OIP36Z7/action/author_attestation","sign_citation":"https://pith.science/pith/PQEUK5B4BLJZPQR4654OIP36Z7/action/citation_signature","submit_replication":"https://pith.science/pith/PQEUK5B4BLJZPQR4654OIP36Z7/action/replication_record"}},"created_at":"2026-05-18T00:04:02.370178+00:00","updated_at":"2026-05-18T00:04:02.370178+00:00"}