{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:TGYPONDD3PR6CBRGROXCE2SJU6","short_pith_number":"pith:TGYPONDD","schema_version":"1.0","canonical_sha256":"99b0f73463dbe3e106268bae226a49a7bbbbd2f834bc1e2658f06f142daa64b9","source":{"kind":"arxiv","id":"1703.07115","version":1},"attestation_state":"computed","paper":{"title":"Layer-wise training of deep networks using kernel similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mandar Kulkarni, Shirish Karande","submitted_at":"2017-03-21T09:53:51Z","abstract_excerpt":"Deep learning has shown promising results in many machine learning applications. The hierarchical feature representation built by deep networks enable compact and precise encoding of the data. A kernel analysis of the trained deep networks demonstrated that with deeper layers, more simple and more accurate data representations are obtained. In this paper, we propose an approach for layer-wise training of a deep network for the supervised classification task. A transformation matrix of each layer is obtained by solving an optimization aimed at a better representation where a subsequent layer bu"},"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":"1703.07115","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-21T09:53:51Z","cross_cats_sorted":[],"title_canon_sha256":"8970ac990ec238dd4d16df980b6fb5ca7e9ac25377e27b75a954bc22e526bf13","abstract_canon_sha256":"51397b282ff5cf7a5870e6ec89c3ed8f6a11dabae52e532fc73056f51ac92954"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:11.276604Z","signature_b64":"QyrHFEsEs6w6aji93UMVFVLSTaALFuqZavYsglhh2SXGPRGcAT6N7VFjdZWEPOcqeeHNY0nWbMwK3M5xl4LFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99b0f73463dbe3e106268bae226a49a7bbbbd2f834bc1e2658f06f142daa64b9","last_reissued_at":"2026-05-18T00:48:11.275920Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:11.275920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Layer-wise training of deep networks using kernel similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mandar Kulkarni, Shirish Karande","submitted_at":"2017-03-21T09:53:51Z","abstract_excerpt":"Deep learning has shown promising results in many machine learning applications. The hierarchical feature representation built by deep networks enable compact and precise encoding of the data. A kernel analysis of the trained deep networks demonstrated that with deeper layers, more simple and more accurate data representations are obtained. In this paper, we propose an approach for layer-wise training of a deep network for the supervised classification task. A transformation matrix of each layer is obtained by solving an optimization aimed at a better representation where a subsequent layer bu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.07115","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":"1703.07115","created_at":"2026-05-18T00:48:11.276007+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.07115v1","created_at":"2026-05-18T00:48:11.276007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.07115","created_at":"2026-05-18T00:48:11.276007+00:00"},{"alias_kind":"pith_short_12","alias_value":"TGYPONDD3PR6","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"TGYPONDD3PR6CBRG","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"TGYPONDD","created_at":"2026-05-18T12:31:46.661854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04038","citing_title":"FLAME: Condensing Ensemble Diversity into a Single Network for Efficient Sequential Recommendation","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TGYPONDD3PR6CBRGROXCE2SJU6","json":"https://pith.science/pith/TGYPONDD3PR6CBRGROXCE2SJU6.json","graph_json":"https://pith.science/api/pith-number/TGYPONDD3PR6CBRGROXCE2SJU6/graph.json","events_json":"https://pith.science/api/pith-number/TGYPONDD3PR6CBRGROXCE2SJU6/events.json","paper":"https://pith.science/paper/TGYPONDD"},"agent_actions":{"view_html":"https://pith.science/pith/TGYPONDD3PR6CBRGROXCE2SJU6","download_json":"https://pith.science/pith/TGYPONDD3PR6CBRGROXCE2SJU6.json","view_paper":"https://pith.science/paper/TGYPONDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.07115&json=true","fetch_graph":"https://pith.science/api/pith-number/TGYPONDD3PR6CBRGROXCE2SJU6/graph.json","fetch_events":"https://pith.science/api/pith-number/TGYPONDD3PR6CBRGROXCE2SJU6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TGYPONDD3PR6CBRGROXCE2SJU6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TGYPONDD3PR6CBRGROXCE2SJU6/action/storage_attestation","attest_author":"https://pith.science/pith/TGYPONDD3PR6CBRGROXCE2SJU6/action/author_attestation","sign_citation":"https://pith.science/pith/TGYPONDD3PR6CBRGROXCE2SJU6/action/citation_signature","submit_replication":"https://pith.science/pith/TGYPONDD3PR6CBRGROXCE2SJU6/action/replication_record"}},"created_at":"2026-05-18T00:48:11.276007+00:00","updated_at":"2026-05-18T00:48:11.276007+00:00"}