{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FTIRUIQMSGUMHXDN437VZRT5R5","short_pith_number":"pith:FTIRUIQM","schema_version":"1.0","canonical_sha256":"2cd11a220c91a8c3dc6de6ff5cc67d8f731799c33143ce7f9578fd42ca280528","source":{"kind":"arxiv","id":"2106.07905","version":1},"attestation_state":"computed","paper":{"title":"Non-Gradient Manifold Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Hongyuan Zhang, Rui Zhang, Xuelong Li, Ziheng Jiao","submitted_at":"2021-06-15T06:39:13Z","abstract_excerpt":"Deep neural network (DNN) generally takes thousands of iterations to optimize via gradient descent and thus has a slow convergence. In addition, softmax, as a decision layer, may ignore the distribution information of the data during classification. Aiming to tackle the referred problems, we propose a novel manifold neural network based on non-gradient optimization, i.e., the closed-form solutions. Considering that the activation function is generally invertible, we reconstruct the network via forward ridge regression and low rank backward approximation, which achieve the rapid convergence. Mo"},"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":"2106.07905","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-15T06:39:13Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"b23541e40d976b7c6a923c87f3b1ce4a83aa57e4a2ea023eb2248fda5bf1318f","abstract_canon_sha256":"f868e6c33a7dc45a028b89ba750c1589c5b3bbe69253c5bd7aadbecab39d8d48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:35.449665Z","signature_b64":"QOMwVAwE84upX5SONnLKp6XTcV7Gbj3DDzUVUveH2HgKhQjXfN6+1Nm+N3TT0fj+Z+71UeMAMPa/ad61sTZiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cd11a220c91a8c3dc6de6ff5cc67d8f731799c33143ce7f9578fd42ca280528","last_reissued_at":"2026-07-05T02:49:35.449160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:35.449160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Gradient Manifold Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Hongyuan Zhang, Rui Zhang, Xuelong Li, Ziheng Jiao","submitted_at":"2021-06-15T06:39:13Z","abstract_excerpt":"Deep neural network (DNN) generally takes thousands of iterations to optimize via gradient descent and thus has a slow convergence. In addition, softmax, as a decision layer, may ignore the distribution information of the data during classification. Aiming to tackle the referred problems, we propose a novel manifold neural network based on non-gradient optimization, i.e., the closed-form solutions. Considering that the activation function is generally invertible, we reconstruct the network via forward ridge regression and low rank backward approximation, which achieve the rapid convergence. Mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07905","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/2106.07905/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":"2106.07905","created_at":"2026-07-05T02:49:35.449221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.07905v1","created_at":"2026-07-05T02:49:35.449221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07905","created_at":"2026-07-05T02:49:35.449221+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTIRUIQMSGUM","created_at":"2026-07-05T02:49:35.449221+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTIRUIQMSGUMHXDN","created_at":"2026-07-05T02:49:35.449221+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTIRUIQM","created_at":"2026-07-05T02:49:35.449221+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/FTIRUIQMSGUMHXDN437VZRT5R5","json":"https://pith.science/pith/FTIRUIQMSGUMHXDN437VZRT5R5.json","graph_json":"https://pith.science/api/pith-number/FTIRUIQMSGUMHXDN437VZRT5R5/graph.json","events_json":"https://pith.science/api/pith-number/FTIRUIQMSGUMHXDN437VZRT5R5/events.json","paper":"https://pith.science/paper/FTIRUIQM"},"agent_actions":{"view_html":"https://pith.science/pith/FTIRUIQMSGUMHXDN437VZRT5R5","download_json":"https://pith.science/pith/FTIRUIQMSGUMHXDN437VZRT5R5.json","view_paper":"https://pith.science/paper/FTIRUIQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.07905&json=true","fetch_graph":"https://pith.science/api/pith-number/FTIRUIQMSGUMHXDN437VZRT5R5/graph.json","fetch_events":"https://pith.science/api/pith-number/FTIRUIQMSGUMHXDN437VZRT5R5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTIRUIQMSGUMHXDN437VZRT5R5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTIRUIQMSGUMHXDN437VZRT5R5/action/storage_attestation","attest_author":"https://pith.science/pith/FTIRUIQMSGUMHXDN437VZRT5R5/action/author_attestation","sign_citation":"https://pith.science/pith/FTIRUIQMSGUMHXDN437VZRT5R5/action/citation_signature","submit_replication":"https://pith.science/pith/FTIRUIQMSGUMHXDN437VZRT5R5/action/replication_record"}},"created_at":"2026-07-05T02:49:35.449221+00:00","updated_at":"2026-07-05T02:49:35.449221+00:00"}