{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WNXHY2RDOZO7ZCGIAWCKCPYRB2","short_pith_number":"pith:WNXHY2RD","schema_version":"1.0","canonical_sha256":"b36e7c6a23765dfc88c80584a13f110ea0f06b4a4584c3a1b5405eaf4bf27031","source":{"kind":"arxiv","id":"2004.06632","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Activation Functions and their relation with Xavier and He Normal Initialization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Leonid Datta","submitted_at":"2020-03-18T18:17:56Z","abstract_excerpt":"In artificial neural network, the activation function and the weight initialization method play important roles in training and performance of a neural network. The question arises is what properties of a function are important/necessary for being a well-performing activation function. Also, the most widely used weight initialization methods - Xavier and He normal initialization have fundamental connection with activation function. This survey discusses the important/necessary properties of activation function and the most widely used activation functions (sigmoid, tanh, ReLU, LReLU and PReLU)"},"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":"2004.06632","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.NE","submitted_at":"2020-03-18T18:17:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8a9533b5af70e5abfb522f4b1f8d8f971cf251ffd462ff56df4efeeeb77811cf","abstract_canon_sha256":"31a4e1f8312bab515442a57d21dd41150a4e38fd329cebff7f8426c01c404361"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:54.101187Z","signature_b64":"d9R74JDRgQ2ABj4KCOh36QmqRyc8pB8zbCjysYDTZZruAydLgvudTxeTQH+csWMPgGLRHjPKpP7ZLBiLWDw8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b36e7c6a23765dfc88c80584a13f110ea0f06b4a4584c3a1b5405eaf4bf27031","last_reissued_at":"2026-07-05T00:54:54.100728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:54.100728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Activation Functions and their relation with Xavier and He Normal Initialization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Leonid Datta","submitted_at":"2020-03-18T18:17:56Z","abstract_excerpt":"In artificial neural network, the activation function and the weight initialization method play important roles in training and performance of a neural network. The question arises is what properties of a function are important/necessary for being a well-performing activation function. Also, the most widely used weight initialization methods - Xavier and He normal initialization have fundamental connection with activation function. This survey discusses the important/necessary properties of activation function and the most widely used activation functions (sigmoid, tanh, ReLU, LReLU and PReLU)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.06632","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.06632/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":"2004.06632","created_at":"2026-07-05T00:54:54.100785+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.06632v1","created_at":"2026-07-05T00:54:54.100785+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.06632","created_at":"2026-07-05T00:54:54.100785+00:00"},{"alias_kind":"pith_short_12","alias_value":"WNXHY2RDOZO7","created_at":"2026-07-05T00:54:54.100785+00:00"},{"alias_kind":"pith_short_16","alias_value":"WNXHY2RDOZO7ZCGI","created_at":"2026-07-05T00:54:54.100785+00:00"},{"alias_kind":"pith_short_8","alias_value":"WNXHY2RD","created_at":"2026-07-05T00:54:54.100785+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23359","citing_title":"Adaptive Hard-Soft Physics-Informed Neural Networks for Robust Boundary-Constrained PDE Solving","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WNXHY2RDOZO7ZCGIAWCKCPYRB2","json":"https://pith.science/pith/WNXHY2RDOZO7ZCGIAWCKCPYRB2.json","graph_json":"https://pith.science/api/pith-number/WNXHY2RDOZO7ZCGIAWCKCPYRB2/graph.json","events_json":"https://pith.science/api/pith-number/WNXHY2RDOZO7ZCGIAWCKCPYRB2/events.json","paper":"https://pith.science/paper/WNXHY2RD"},"agent_actions":{"view_html":"https://pith.science/pith/WNXHY2RDOZO7ZCGIAWCKCPYRB2","download_json":"https://pith.science/pith/WNXHY2RDOZO7ZCGIAWCKCPYRB2.json","view_paper":"https://pith.science/paper/WNXHY2RD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.06632&json=true","fetch_graph":"https://pith.science/api/pith-number/WNXHY2RDOZO7ZCGIAWCKCPYRB2/graph.json","fetch_events":"https://pith.science/api/pith-number/WNXHY2RDOZO7ZCGIAWCKCPYRB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WNXHY2RDOZO7ZCGIAWCKCPYRB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WNXHY2RDOZO7ZCGIAWCKCPYRB2/action/storage_attestation","attest_author":"https://pith.science/pith/WNXHY2RDOZO7ZCGIAWCKCPYRB2/action/author_attestation","sign_citation":"https://pith.science/pith/WNXHY2RDOZO7ZCGIAWCKCPYRB2/action/citation_signature","submit_replication":"https://pith.science/pith/WNXHY2RDOZO7ZCGIAWCKCPYRB2/action/replication_record"}},"created_at":"2026-07-05T00:54:54.100785+00:00","updated_at":"2026-07-05T00:54:54.100785+00:00"}