{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3TIN7EKXM2BJM7ZSNWKMZV757U","short_pith_number":"pith:3TIN7EKX","schema_version":"1.0","canonical_sha256":"dcd0df91576682967f326d94ccd7fdfd192de6e519ea50b853012daa77216fdb","source":{"kind":"arxiv","id":"1908.02400","version":1},"attestation_state":"computed","paper":{"title":"Refining the Structure of Neural Networks Using Matrix Conditioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dianne P O'Leary, Roozbeh Yousefzadeh","submitted_at":"2019-08-06T23:45:34Z","abstract_excerpt":"Deep learning models have proven to be exceptionally useful in performing many machine learning tasks. However, for each new dataset, choosing an effective size and structure of the model can be a time-consuming process of trial and error. While a small network with few neurons might not be able to capture the intricacies of a given task, having too many neurons can lead to overfitting and poor generalization. Here, we propose a practical method that employs matrix conditioning to automatically design the structure of layers of a feed-forward network, by first adjusting the proportion of neuro"},"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":"1908.02400","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-06T23:45:34Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"4c8b815d72186c8e75f1ffbddb8c7d02e8f4f26eaaf712d9a53387b2f8fbee40","abstract_canon_sha256":"ce69064adba2ba3318f7c02f35d289ed7729a392922635f3a1bc50129a7eb51a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:52:08.442475Z","signature_b64":"ZtG0fRMcgeM0dkmj2+TcTqJrHWzrAusVxniGhK9OLD21arf4hXDzdPwsMuWNlXsdtW/rdtlpHxQG1cYHsOgfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcd0df91576682967f326d94ccd7fdfd192de6e519ea50b853012daa77216fdb","last_reissued_at":"2026-07-04T23:52:08.442113Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:52:08.442113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Refining the Structure of Neural Networks Using Matrix Conditioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dianne P O'Leary, Roozbeh Yousefzadeh","submitted_at":"2019-08-06T23:45:34Z","abstract_excerpt":"Deep learning models have proven to be exceptionally useful in performing many machine learning tasks. However, for each new dataset, choosing an effective size and structure of the model can be a time-consuming process of trial and error. While a small network with few neurons might not be able to capture the intricacies of a given task, having too many neurons can lead to overfitting and poor generalization. Here, we propose a practical method that employs matrix conditioning to automatically design the structure of layers of a feed-forward network, by first adjusting the proportion of neuro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02400","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/1908.02400/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":"1908.02400","created_at":"2026-07-04T23:52:08.442169+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.02400v1","created_at":"2026-07-04T23:52:08.442169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02400","created_at":"2026-07-04T23:52:08.442169+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TIN7EKXM2BJ","created_at":"2026-07-04T23:52:08.442169+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TIN7EKXM2BJM7ZS","created_at":"2026-07-04T23:52:08.442169+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TIN7EKX","created_at":"2026-07-04T23:52:08.442169+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/3TIN7EKXM2BJM7ZSNWKMZV757U","json":"https://pith.science/pith/3TIN7EKXM2BJM7ZSNWKMZV757U.json","graph_json":"https://pith.science/api/pith-number/3TIN7EKXM2BJM7ZSNWKMZV757U/graph.json","events_json":"https://pith.science/api/pith-number/3TIN7EKXM2BJM7ZSNWKMZV757U/events.json","paper":"https://pith.science/paper/3TIN7EKX"},"agent_actions":{"view_html":"https://pith.science/pith/3TIN7EKXM2BJM7ZSNWKMZV757U","download_json":"https://pith.science/pith/3TIN7EKXM2BJM7ZSNWKMZV757U.json","view_paper":"https://pith.science/paper/3TIN7EKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.02400&json=true","fetch_graph":"https://pith.science/api/pith-number/3TIN7EKXM2BJM7ZSNWKMZV757U/graph.json","fetch_events":"https://pith.science/api/pith-number/3TIN7EKXM2BJM7ZSNWKMZV757U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TIN7EKXM2BJM7ZSNWKMZV757U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TIN7EKXM2BJM7ZSNWKMZV757U/action/storage_attestation","attest_author":"https://pith.science/pith/3TIN7EKXM2BJM7ZSNWKMZV757U/action/author_attestation","sign_citation":"https://pith.science/pith/3TIN7EKXM2BJM7ZSNWKMZV757U/action/citation_signature","submit_replication":"https://pith.science/pith/3TIN7EKXM2BJM7ZSNWKMZV757U/action/replication_record"}},"created_at":"2026-07-04T23:52:08.442169+00:00","updated_at":"2026-07-04T23:52:08.442169+00:00"}