{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:GQZJL46P3ON6N5N4GLHBQUBOG5","short_pith_number":"pith:GQZJL46P","schema_version":"1.0","canonical_sha256":"343295f3cfdb9be6f5bc32ce18502e376fe58b20dbef35e49f9cd0c134d82a0a","source":{"kind":"arxiv","id":"1512.07030","version":1},"attestation_state":"computed","paper":{"title":"Deep Learning with S-shaped Rectified Linear Activation Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyan Xu, Jiashi Feng, Junjun Xiong, Shuicheng Yan, Xiaojie Jin, Yunchao Wei","submitted_at":"2015-12-22T10:54:26Z","abstract_excerpt":"Rectified linear activation units are important components for state-of-the-art deep convolutional networks. In this paper, we propose a novel S-shaped rectified linear activation unit (SReLU) to learn both convex and non-convex functions, imitating the multiple function forms given by the two fundamental laws, namely the Webner-Fechner law and the Stevens law, in psychophysics and neural sciences. Specifically, SReLU consists of three piecewise linear functions, which are formulated by four learnable parameters. The SReLU is learned jointly with the training of the whole deep network through "},"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":"1512.07030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-22T10:54:26Z","cross_cats_sorted":[],"title_canon_sha256":"10510deff19b04b6839391516aff7b53dc0d22af970fbfa2ff57e6799f9f7e76","abstract_canon_sha256":"6f3e82ead9dbf9683a2410a47dbf91883591b419be16188e1d66c04401307d91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:23:53.101001Z","signature_b64":"gom3MGwqHJtqfnZ5yZNF/xecmcp+dA6tITbHEXoB5kLQGm8EYrpng7ztbzObtm37xxqqwUJuG57pYOucime+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"343295f3cfdb9be6f5bc32ce18502e376fe58b20dbef35e49f9cd0c134d82a0a","last_reissued_at":"2026-05-18T01:23:53.100399Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:23:53.100399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Learning with S-shaped Rectified Linear Activation Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyan Xu, Jiashi Feng, Junjun Xiong, Shuicheng Yan, Xiaojie Jin, Yunchao Wei","submitted_at":"2015-12-22T10:54:26Z","abstract_excerpt":"Rectified linear activation units are important components for state-of-the-art deep convolutional networks. In this paper, we propose a novel S-shaped rectified linear activation unit (SReLU) to learn both convex and non-convex functions, imitating the multiple function forms given by the two fundamental laws, namely the Webner-Fechner law and the Stevens law, in psychophysics and neural sciences. Specifically, SReLU consists of three piecewise linear functions, which are formulated by four learnable parameters. The SReLU is learned jointly with the training of the whole deep network through "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.07030","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":"1512.07030","created_at":"2026-05-18T01:23:53.100484+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.07030v1","created_at":"2026-05-18T01:23:53.100484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.07030","created_at":"2026-05-18T01:23:53.100484+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQZJL46P3ON6","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQZJL46P3ON6N5N4","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQZJL46P","created_at":"2026-05-18T12:29:22.688609+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/GQZJL46P3ON6N5N4GLHBQUBOG5","json":"https://pith.science/pith/GQZJL46P3ON6N5N4GLHBQUBOG5.json","graph_json":"https://pith.science/api/pith-number/GQZJL46P3ON6N5N4GLHBQUBOG5/graph.json","events_json":"https://pith.science/api/pith-number/GQZJL46P3ON6N5N4GLHBQUBOG5/events.json","paper":"https://pith.science/paper/GQZJL46P"},"agent_actions":{"view_html":"https://pith.science/pith/GQZJL46P3ON6N5N4GLHBQUBOG5","download_json":"https://pith.science/pith/GQZJL46P3ON6N5N4GLHBQUBOG5.json","view_paper":"https://pith.science/paper/GQZJL46P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.07030&json=true","fetch_graph":"https://pith.science/api/pith-number/GQZJL46P3ON6N5N4GLHBQUBOG5/graph.json","fetch_events":"https://pith.science/api/pith-number/GQZJL46P3ON6N5N4GLHBQUBOG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQZJL46P3ON6N5N4GLHBQUBOG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQZJL46P3ON6N5N4GLHBQUBOG5/action/storage_attestation","attest_author":"https://pith.science/pith/GQZJL46P3ON6N5N4GLHBQUBOG5/action/author_attestation","sign_citation":"https://pith.science/pith/GQZJL46P3ON6N5N4GLHBQUBOG5/action/citation_signature","submit_replication":"https://pith.science/pith/GQZJL46P3ON6N5N4GLHBQUBOG5/action/replication_record"}},"created_at":"2026-05-18T01:23:53.100484+00:00","updated_at":"2026-05-18T01:23:53.100484+00:00"}