{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ZDSJGYUVABGU42J23JI2YCG7GA","short_pith_number":"pith:ZDSJGYUV","schema_version":"1.0","canonical_sha256":"c8e4936295004d4e693ada51ac08df303ccfff9fb836005d2d6f7baff03bf105","source":{"kind":"arxiv","id":"1710.10686","version":1},"attestation_state":"computed","paper":{"title":"Regularization for Deep Learning: A Taxonomy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Cremers, Jan Kuka\\v{c}ka, Vladimir Golkov","submitted_at":"2017-10-29T20:27:51Z","abstract_excerpt":"Regularization is one of the crucial ingredients of deep learning, yet the term regularization has various definitions, and regularization methods are often studied separately from each other. In our work we present a systematic, unifying taxonomy to categorize existing methods. We distinguish methods that affect data, network architectures, error terms, regularization terms, and optimization procedures. We do not provide all details about the listed methods; instead, we present an overview of how the methods can be sorted into meaningful categories and sub-categories. This helps revealing lin"},"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":"1710.10686","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-29T20:27:51Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"dd984c1605235c2870126a6c156124e67f7d81a65a5b42cbd36415de34f30cad","abstract_canon_sha256":"d0c93711901942d3275bb27585170097bcb619442d4c2c24651ab1a126d69542"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:46.755357Z","signature_b64":"QvADItzVtKyRo+Y3KcE6kLkeT+W2wgZA8wVjXjIQw4njnfvYgtI/bB1yEigYm/hLKKp6KDLZwLR/OTTOiSB3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8e4936295004d4e693ada51ac08df303ccfff9fb836005d2d6f7baff03bf105","last_reissued_at":"2026-05-18T00:31:46.754710Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:46.754710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regularization for Deep Learning: A Taxonomy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Cremers, Jan Kuka\\v{c}ka, Vladimir Golkov","submitted_at":"2017-10-29T20:27:51Z","abstract_excerpt":"Regularization is one of the crucial ingredients of deep learning, yet the term regularization has various definitions, and regularization methods are often studied separately from each other. In our work we present a systematic, unifying taxonomy to categorize existing methods. We distinguish methods that affect data, network architectures, error terms, regularization terms, and optimization procedures. We do not provide all details about the listed methods; instead, we present an overview of how the methods can be sorted into meaningful categories and sub-categories. This helps revealing lin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10686","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":"1710.10686","created_at":"2026-05-18T00:31:46.754802+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.10686v1","created_at":"2026-05-18T00:31:46.754802+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10686","created_at":"2026-05-18T00:31:46.754802+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDSJGYUVABGU","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDSJGYUVABGU42J2","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDSJGYUV","created_at":"2026-05-18T12:31:59.375834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2202.02710","citing_title":"Spectrally Adapted Physics-Informed Neural Networks for Solving Unbounded Domain Problems","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZDSJGYUVABGU42J23JI2YCG7GA","json":"https://pith.science/pith/ZDSJGYUVABGU42J23JI2YCG7GA.json","graph_json":"https://pith.science/api/pith-number/ZDSJGYUVABGU42J23JI2YCG7GA/graph.json","events_json":"https://pith.science/api/pith-number/ZDSJGYUVABGU42J23JI2YCG7GA/events.json","paper":"https://pith.science/paper/ZDSJGYUV"},"agent_actions":{"view_html":"https://pith.science/pith/ZDSJGYUVABGU42J23JI2YCG7GA","download_json":"https://pith.science/pith/ZDSJGYUVABGU42J23JI2YCG7GA.json","view_paper":"https://pith.science/paper/ZDSJGYUV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.10686&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDSJGYUVABGU42J23JI2YCG7GA/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDSJGYUVABGU42J23JI2YCG7GA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDSJGYUVABGU42J23JI2YCG7GA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDSJGYUVABGU42J23JI2YCG7GA/action/storage_attestation","attest_author":"https://pith.science/pith/ZDSJGYUVABGU42J23JI2YCG7GA/action/author_attestation","sign_citation":"https://pith.science/pith/ZDSJGYUVABGU42J23JI2YCG7GA/action/citation_signature","submit_replication":"https://pith.science/pith/ZDSJGYUVABGU42J23JI2YCG7GA/action/replication_record"}},"created_at":"2026-05-18T00:31:46.754802+00:00","updated_at":"2026-05-18T00:31:46.754802+00:00"}