{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:J2SYGSBVW4K27C36HZU2UWYUOU","short_pith_number":"pith:J2SYGSBV","schema_version":"1.0","canonical_sha256":"4ea5834835b715af8b7e3e69aa5b1475381cac646672f00b3a5c2e9872fd6b59","source":{"kind":"arxiv","id":"1810.02786","version":2},"attestation_state":"computed","paper":{"title":"Interpretable Convolutional Neural Networks via Feedforward Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"C.-C. Jay Kuo, Jiali Duan, Min Zhang, Siyang Li, Yueru Chen","submitted_at":"2018-10-05T16:44:49Z","abstract_excerpt":"The model parameters of convolutional neural networks (CNNs) are determined by backpropagation (BP). In this work, we propose an interpretable feedforward (FF) design without any BP as a reference. The FF design adopts a data-centric approach. It derives network parameters of the current layer based on data statistics from the output of the previous layer in a one-pass manner. To construct convolutional layers, we develop a new signal transform, called the Saab (Subspace Approximation with Adjusted Bias) transform. It is a variant of the principal component analysis (PCA) with an added bias ve"},"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":"1810.02786","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-05T16:44:49Z","cross_cats_sorted":[],"title_canon_sha256":"b0419da30c37310085d7526ea40a1070059233fc7414966c84182400adc5c429","abstract_canon_sha256":"43e3f589e4bc51ba90dedf6ce2fe511510d965d417faa99c0252000492a70d90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:44.154922Z","signature_b64":"ZxHp5lMEXK7dG80AlOeem+HWCJpF/YUoWHgh2eAW7lwzD0Y/ENgeIMRL3xJPc8pHwHUVnNiLMWAUK07LCiamBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ea5834835b715af8b7e3e69aa5b1475381cac646672f00b3a5c2e9872fd6b59","last_reissued_at":"2026-05-18T00:02:44.154304Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:44.154304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Convolutional Neural Networks via Feedforward Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"C.-C. Jay Kuo, Jiali Duan, Min Zhang, Siyang Li, Yueru Chen","submitted_at":"2018-10-05T16:44:49Z","abstract_excerpt":"The model parameters of convolutional neural networks (CNNs) are determined by backpropagation (BP). In this work, we propose an interpretable feedforward (FF) design without any BP as a reference. The FF design adopts a data-centric approach. It derives network parameters of the current layer based on data statistics from the output of the previous layer in a one-pass manner. To construct convolutional layers, we develop a new signal transform, called the Saab (Subspace Approximation with Adjusted Bias) transform. It is a variant of the principal component analysis (PCA) with an added bias ve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.02786","kind":"arxiv","version":2},"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":"1810.02786","created_at":"2026-05-18T00:02:44.154418+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.02786v2","created_at":"2026-05-18T00:02:44.154418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.02786","created_at":"2026-05-18T00:02:44.154418+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2SYGSBVW4K2","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2SYGSBVW4K27C36","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2SYGSBV","created_at":"2026-05-18T12:32:31.084164+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/J2SYGSBVW4K27C36HZU2UWYUOU","json":"https://pith.science/pith/J2SYGSBVW4K27C36HZU2UWYUOU.json","graph_json":"https://pith.science/api/pith-number/J2SYGSBVW4K27C36HZU2UWYUOU/graph.json","events_json":"https://pith.science/api/pith-number/J2SYGSBVW4K27C36HZU2UWYUOU/events.json","paper":"https://pith.science/paper/J2SYGSBV"},"agent_actions":{"view_html":"https://pith.science/pith/J2SYGSBVW4K27C36HZU2UWYUOU","download_json":"https://pith.science/pith/J2SYGSBVW4K27C36HZU2UWYUOU.json","view_paper":"https://pith.science/paper/J2SYGSBV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.02786&json=true","fetch_graph":"https://pith.science/api/pith-number/J2SYGSBVW4K27C36HZU2UWYUOU/graph.json","fetch_events":"https://pith.science/api/pith-number/J2SYGSBVW4K27C36HZU2UWYUOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2SYGSBVW4K27C36HZU2UWYUOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2SYGSBVW4K27C36HZU2UWYUOU/action/storage_attestation","attest_author":"https://pith.science/pith/J2SYGSBVW4K27C36HZU2UWYUOU/action/author_attestation","sign_citation":"https://pith.science/pith/J2SYGSBVW4K27C36HZU2UWYUOU/action/citation_signature","submit_replication":"https://pith.science/pith/J2SYGSBVW4K27C36HZU2UWYUOU/action/replication_record"}},"created_at":"2026-05-18T00:02:44.154418+00:00","updated_at":"2026-05-18T00:02:44.154418+00:00"}