{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:64VPN3U2U7EATTMGVM6P5SRKQC","short_pith_number":"pith:64VPN3U2","schema_version":"1.0","canonical_sha256":"f72af6ee9aa7c809cd86ab3cfeca2a80a898b3e1c4a9a5c204f8da563a14891a","source":{"kind":"arxiv","id":"1708.01666","version":5},"attestation_state":"computed","paper":{"title":"An Effective Training Method For Deep Convolutional Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jie Cao, Kun Gao, Qun Hao, Xi Chen, Yang Jiang, Zeyang Dou","submitted_at":"2017-07-31T23:19:03Z","abstract_excerpt":"In this paper, we propose the nonlinearity generation method to speed up and stabilize the training of deep convolutional neural networks. The proposed method modifies a family of activation functions as nonlinearity generators (NGs). NGs make the activation functions linear symmetric for their inputs to lower model capacity, and automatically introduce nonlinearity to enhance the capacity of the model during training. The proposed method can be considered an unusual form of regularization: the model parameters are obtained by training a relatively low-capacity model, that is relatively easy t"},"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":"1708.01666","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-31T23:19:03Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"dc4283e35c32b3091247690c0ffc435017b27bc7f3d538af2dad2bcff5471cdc","abstract_canon_sha256":"10bfa16a3fdf89e00f3e08174c12003c756d9f9771d17b6d821f86fa02e20c15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:39.522304Z","signature_b64":"79HgczIp6CUmb0n1phvHybPLZ+Ypw86ETfFSf/Y6VJ9tFsT7c85atIfuQrRepbZI4nfOd5l9rcHAq+cdcphgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f72af6ee9aa7c809cd86ab3cfeca2a80a898b3e1c4a9a5c204f8da563a14891a","last_reissued_at":"2026-05-18T00:32:39.521716Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:39.521716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Effective Training Method For Deep Convolutional Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jie Cao, Kun Gao, Qun Hao, Xi Chen, Yang Jiang, Zeyang Dou","submitted_at":"2017-07-31T23:19:03Z","abstract_excerpt":"In this paper, we propose the nonlinearity generation method to speed up and stabilize the training of deep convolutional neural networks. The proposed method modifies a family of activation functions as nonlinearity generators (NGs). NGs make the activation functions linear symmetric for their inputs to lower model capacity, and automatically introduce nonlinearity to enhance the capacity of the model during training. The proposed method can be considered an unusual form of regularization: the model parameters are obtained by training a relatively low-capacity model, that is relatively easy t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01666","kind":"arxiv","version":5},"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":"1708.01666","created_at":"2026-05-18T00:32:39.521819+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.01666v5","created_at":"2026-05-18T00:32:39.521819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01666","created_at":"2026-05-18T00:32:39.521819+00:00"},{"alias_kind":"pith_short_12","alias_value":"64VPN3U2U7EA","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"64VPN3U2U7EATTMG","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"64VPN3U2","created_at":"2026-05-18T12:31:03.183658+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/64VPN3U2U7EATTMGVM6P5SRKQC","json":"https://pith.science/pith/64VPN3U2U7EATTMGVM6P5SRKQC.json","graph_json":"https://pith.science/api/pith-number/64VPN3U2U7EATTMGVM6P5SRKQC/graph.json","events_json":"https://pith.science/api/pith-number/64VPN3U2U7EATTMGVM6P5SRKQC/events.json","paper":"https://pith.science/paper/64VPN3U2"},"agent_actions":{"view_html":"https://pith.science/pith/64VPN3U2U7EATTMGVM6P5SRKQC","download_json":"https://pith.science/pith/64VPN3U2U7EATTMGVM6P5SRKQC.json","view_paper":"https://pith.science/paper/64VPN3U2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.01666&json=true","fetch_graph":"https://pith.science/api/pith-number/64VPN3U2U7EATTMGVM6P5SRKQC/graph.json","fetch_events":"https://pith.science/api/pith-number/64VPN3U2U7EATTMGVM6P5SRKQC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/64VPN3U2U7EATTMGVM6P5SRKQC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/64VPN3U2U7EATTMGVM6P5SRKQC/action/storage_attestation","attest_author":"https://pith.science/pith/64VPN3U2U7EATTMGVM6P5SRKQC/action/author_attestation","sign_citation":"https://pith.science/pith/64VPN3U2U7EATTMGVM6P5SRKQC/action/citation_signature","submit_replication":"https://pith.science/pith/64VPN3U2U7EATTMGVM6P5SRKQC/action/replication_record"}},"created_at":"2026-05-18T00:32:39.521819+00:00","updated_at":"2026-05-18T00:32:39.521819+00:00"}