{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7QIVXZ3ZEDO5OCOU73OGQTPILC","short_pith_number":"pith:7QIVXZ3Z","schema_version":"1.0","canonical_sha256":"fc115be77920ddd709d4fedc684de8588df26a359383ffff35c1b65649dfca5a","source":{"kind":"arxiv","id":"1807.03973","version":2},"attestation_state":"computed","paper":{"title":"ReLU Deep Neural Networks and Linear Finite Elements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Chunyue Zheng, Jinchao Xu, Juncai He, Lin Li","submitted_at":"2018-07-11T07:32:40Z","abstract_excerpt":"In this paper, we investigate the relationship between deep neural networks (DNN) with rectified linear unit (ReLU) function as the activation function and continuous piecewise linear (CPWL) functions, especially CPWL functions from the simplicial linear finite element method (FEM). We first consider the special case of FEM. By exploring the DNN representation of its nodal basis functions, we present a ReLU DNN representation of CPWL in FEM. We theoretically establish that at least $2$ hidden layers are needed in a ReLU DNN to represent any linear finite element functions in $\\Omega \\subseteq "},"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":"1807.03973","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2018-07-11T07:32:40Z","cross_cats_sorted":["cs.NA"],"title_canon_sha256":"b5ff544a1ba0e12a3371fb5377cb08f7955a2a0825c5eefef7301504c0881503","abstract_canon_sha256":"bc0497acc8461cca21539a14fb89c38f1bf841be69d2fdf4776cfc2b6af88c96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T19:12:06.597428Z","signature_b64":"qMViK252it6DNPbc2Mz1GtQWy2aiUyhvByRW+YbopCDMOzflmW96WpNW9Mby3mo8RIHhLTOaBv35FevUzcV8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc115be77920ddd709d4fedc684de8588df26a359383ffff35c1b65649dfca5a","last_reissued_at":"2026-06-04T19:12:06.596965Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T19:12:06.596965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReLU Deep Neural Networks and Linear Finite Elements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA"],"primary_cat":"math.NA","authors_text":"Chunyue Zheng, Jinchao Xu, Juncai He, Lin Li","submitted_at":"2018-07-11T07:32:40Z","abstract_excerpt":"In this paper, we investigate the relationship between deep neural networks (DNN) with rectified linear unit (ReLU) function as the activation function and continuous piecewise linear (CPWL) functions, especially CPWL functions from the simplicial linear finite element method (FEM). We first consider the special case of FEM. By exploring the DNN representation of its nodal basis functions, we present a ReLU DNN representation of CPWL in FEM. We theoretically establish that at least $2$ hidden layers are needed in a ReLU DNN to represent any linear finite element functions in $\\Omega \\subseteq "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03973","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1807.03973/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1807.03973","created_at":"2026-06-04T19:12:06.597025+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.03973v2","created_at":"2026-06-04T19:12:06.597025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03973","created_at":"2026-06-04T19:12:06.597025+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QIVXZ3ZEDO5","created_at":"2026-06-04T19:12:06.597025+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QIVXZ3ZEDO5OCOU","created_at":"2026-06-04T19:12:06.597025+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QIVXZ3Z","created_at":"2026-06-04T19:12:06.597025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1906.09235","citing_title":"Theory of the Frequency Principle for General Deep Neural Networks","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2212.08989","citing_title":"Deep learning applied to computational mechanics: A comprehensive review, state of the art, and the classics","ref_index":282,"is_internal_anchor":true},{"citing_arxiv_id":"2505.17556","citing_title":"Wildfire spread forecasting with Deep Learning","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2404.19756","citing_title":"KAN: Kolmogorov-Arnold Networks","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7QIVXZ3ZEDO5OCOU73OGQTPILC","json":"https://pith.science/pith/7QIVXZ3ZEDO5OCOU73OGQTPILC.json","graph_json":"https://pith.science/api/pith-number/7QIVXZ3ZEDO5OCOU73OGQTPILC/graph.json","events_json":"https://pith.science/api/pith-number/7QIVXZ3ZEDO5OCOU73OGQTPILC/events.json","paper":"https://pith.science/paper/7QIVXZ3Z"},"agent_actions":{"view_html":"https://pith.science/pith/7QIVXZ3ZEDO5OCOU73OGQTPILC","download_json":"https://pith.science/pith/7QIVXZ3ZEDO5OCOU73OGQTPILC.json","view_paper":"https://pith.science/paper/7QIVXZ3Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.03973&json=true","fetch_graph":"https://pith.science/api/pith-number/7QIVXZ3ZEDO5OCOU73OGQTPILC/graph.json","fetch_events":"https://pith.science/api/pith-number/7QIVXZ3ZEDO5OCOU73OGQTPILC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QIVXZ3ZEDO5OCOU73OGQTPILC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QIVXZ3ZEDO5OCOU73OGQTPILC/action/storage_attestation","attest_author":"https://pith.science/pith/7QIVXZ3ZEDO5OCOU73OGQTPILC/action/author_attestation","sign_citation":"https://pith.science/pith/7QIVXZ3ZEDO5OCOU73OGQTPILC/action/citation_signature","submit_replication":"https://pith.science/pith/7QIVXZ3ZEDO5OCOU73OGQTPILC/action/replication_record"}},"created_at":"2026-06-04T19:12:06.597025+00:00","updated_at":"2026-06-04T19:12:06.597025+00:00"}