{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:MHZUV32JL5G3UCFPNNYY6SW3AR","short_pith_number":"pith:MHZUV32J","schema_version":"1.0","canonical_sha256":"61f34aef495f4dba08af6b718f4adb045b6361becb76c29ab4aa47944ec14e79","source":{"kind":"arxiv","id":"1512.09194","version":2},"attestation_state":"computed","paper":{"title":"Exploiting Local Structures with the Kronecker Layer in Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia-Nan Wu, Shuchang Zhou, Xinyu Zhou, Yuxin Wu","submitted_at":"2015-12-31T01:32:16Z","abstract_excerpt":"In this paper, we propose and study a technique to reduce the number of parameters and computation time in convolutional neural networks. We use Kronecker product to exploit the local structures within convolution and fully-connected layers, by replacing the large weight matrices by combinations of multiple Kronecker products of smaller matrices. Just as the Kronecker product is a generalization of the outer product from vectors to matrices, our method is a generalization of the low rank approximation method for convolution neural networks. We also introduce combinations of different shapes of"},"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":"1512.09194","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-31T01:32:16Z","cross_cats_sorted":[],"title_canon_sha256":"8b62a81b6de0c862b8d6332b4cc8f03678a1bd3e0c5151fc51054b2308006024","abstract_canon_sha256":"a0e98ba212eaaa7066d4e07c4f541771b5d5f3093ce4cffe9865141cd825d14c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:21:19.059786Z","signature_b64":"nuTs6B+lmeF6HK+2HEmffvhl7TjmJKdEP+Q7Mv4amkGzBTp7kGLSIME6HMl+PMu1EEz0D1tFoNM7yWZfZgiSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61f34aef495f4dba08af6b718f4adb045b6361becb76c29ab4aa47944ec14e79","last_reissued_at":"2026-05-18T01:21:19.059224Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:21:19.059224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Local Structures with the Kronecker Layer in Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia-Nan Wu, Shuchang Zhou, Xinyu Zhou, Yuxin Wu","submitted_at":"2015-12-31T01:32:16Z","abstract_excerpt":"In this paper, we propose and study a technique to reduce the number of parameters and computation time in convolutional neural networks. We use Kronecker product to exploit the local structures within convolution and fully-connected layers, by replacing the large weight matrices by combinations of multiple Kronecker products of smaller matrices. Just as the Kronecker product is a generalization of the outer product from vectors to matrices, our method is a generalization of the low rank approximation method for convolution neural networks. We also introduce combinations of different shapes of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.09194","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":"1512.09194","created_at":"2026-05-18T01:21:19.059297+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.09194v2","created_at":"2026-05-18T01:21:19.059297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.09194","created_at":"2026-05-18T01:21:19.059297+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHZUV32JL5G3","created_at":"2026-05-18T12:29:32.376354+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHZUV32JL5G3UCFP","created_at":"2026-05-18T12:29:32.376354+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHZUV32J","created_at":"2026-05-18T12:29:32.376354+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/MHZUV32JL5G3UCFPNNYY6SW3AR","json":"https://pith.science/pith/MHZUV32JL5G3UCFPNNYY6SW3AR.json","graph_json":"https://pith.science/api/pith-number/MHZUV32JL5G3UCFPNNYY6SW3AR/graph.json","events_json":"https://pith.science/api/pith-number/MHZUV32JL5G3UCFPNNYY6SW3AR/events.json","paper":"https://pith.science/paper/MHZUV32J"},"agent_actions":{"view_html":"https://pith.science/pith/MHZUV32JL5G3UCFPNNYY6SW3AR","download_json":"https://pith.science/pith/MHZUV32JL5G3UCFPNNYY6SW3AR.json","view_paper":"https://pith.science/paper/MHZUV32J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.09194&json=true","fetch_graph":"https://pith.science/api/pith-number/MHZUV32JL5G3UCFPNNYY6SW3AR/graph.json","fetch_events":"https://pith.science/api/pith-number/MHZUV32JL5G3UCFPNNYY6SW3AR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHZUV32JL5G3UCFPNNYY6SW3AR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHZUV32JL5G3UCFPNNYY6SW3AR/action/storage_attestation","attest_author":"https://pith.science/pith/MHZUV32JL5G3UCFPNNYY6SW3AR/action/author_attestation","sign_citation":"https://pith.science/pith/MHZUV32JL5G3UCFPNNYY6SW3AR/action/citation_signature","submit_replication":"https://pith.science/pith/MHZUV32JL5G3UCFPNNYY6SW3AR/action/replication_record"}},"created_at":"2026-05-18T01:21:19.059297+00:00","updated_at":"2026-05-18T01:21:19.059297+00:00"}