{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RJ34KLVHJFY5E2ZXFNCSWYL3KC","short_pith_number":"pith:RJ34KLVH","schema_version":"1.0","canonical_sha256":"8a77c52ea74971d26b372b452b617b50b93e94463e218e575381c5b2b036ae25","source":{"kind":"arxiv","id":"1811.00056","version":1},"attestation_state":"computed","paper":{"title":"A Mixture of Expert Approach for Low-Cost Customization of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Azadeh Davoodi, Boyu Zhang, Yu-Hen Hu","submitted_at":"2018-10-31T18:37:28Z","abstract_excerpt":"The ability to customize a trained Deep Neural Network (DNN) locally using user-specific data may greatly enhance user experiences, reduce development costs, and protect user's privacy. In this work, we propose to incorporate a novel Mixture of Experts (MOE) approach to accomplish this goal. This architecture comprises of a Global Expert (GE), a Local Expert (LE) and a Gating Network (GN). The GE is a trained DNN developed on a large training dataset representative of many potential users. After deployment on an embedded edge device, GE will be subject to customized, user-specific data (e.g., "},"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":"1811.00056","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-31T18:37:28Z","cross_cats_sorted":[],"title_canon_sha256":"d3cdc8e7c860f136423240f213a9b0e78f00105747664648775a88ecb88bce56","abstract_canon_sha256":"4c7777b990b134166645351b0aebd64cb31c8561dbd38a42c8293fe0a022d88f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:48.371761Z","signature_b64":"myX4miyxrsj5Mt+3JGXzdaTKBzZUdNZW2HPaN+SJV2PmVmBONRYZ5UspIMcgdpobvOK+VqJ1wAT9QZyoCK2fDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a77c52ea74971d26b372b452b617b50b93e94463e218e575381c5b2b036ae25","last_reissued_at":"2026-05-18T00:01:48.371270Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:48.371270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Mixture of Expert Approach for Low-Cost Customization of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Azadeh Davoodi, Boyu Zhang, Yu-Hen Hu","submitted_at":"2018-10-31T18:37:28Z","abstract_excerpt":"The ability to customize a trained Deep Neural Network (DNN) locally using user-specific data may greatly enhance user experiences, reduce development costs, and protect user's privacy. In this work, we propose to incorporate a novel Mixture of Experts (MOE) approach to accomplish this goal. This architecture comprises of a Global Expert (GE), a Local Expert (LE) and a Gating Network (GN). The GE is a trained DNN developed on a large training dataset representative of many potential users. After deployment on an embedded edge device, GE will be subject to customized, user-specific data (e.g., "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00056","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":"1811.00056","created_at":"2026-05-18T00:01:48.371357+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.00056v1","created_at":"2026-05-18T00:01:48.371357+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00056","created_at":"2026-05-18T00:01:48.371357+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJ34KLVHJFY5","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJ34KLVHJFY5E2ZX","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJ34KLVH","created_at":"2026-05-18T12:32:50.500415+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/RJ34KLVHJFY5E2ZXFNCSWYL3KC","json":"https://pith.science/pith/RJ34KLVHJFY5E2ZXFNCSWYL3KC.json","graph_json":"https://pith.science/api/pith-number/RJ34KLVHJFY5E2ZXFNCSWYL3KC/graph.json","events_json":"https://pith.science/api/pith-number/RJ34KLVHJFY5E2ZXFNCSWYL3KC/events.json","paper":"https://pith.science/paper/RJ34KLVH"},"agent_actions":{"view_html":"https://pith.science/pith/RJ34KLVHJFY5E2ZXFNCSWYL3KC","download_json":"https://pith.science/pith/RJ34KLVHJFY5E2ZXFNCSWYL3KC.json","view_paper":"https://pith.science/paper/RJ34KLVH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.00056&json=true","fetch_graph":"https://pith.science/api/pith-number/RJ34KLVHJFY5E2ZXFNCSWYL3KC/graph.json","fetch_events":"https://pith.science/api/pith-number/RJ34KLVHJFY5E2ZXFNCSWYL3KC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJ34KLVHJFY5E2ZXFNCSWYL3KC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJ34KLVHJFY5E2ZXFNCSWYL3KC/action/storage_attestation","attest_author":"https://pith.science/pith/RJ34KLVHJFY5E2ZXFNCSWYL3KC/action/author_attestation","sign_citation":"https://pith.science/pith/RJ34KLVHJFY5E2ZXFNCSWYL3KC/action/citation_signature","submit_replication":"https://pith.science/pith/RJ34KLVHJFY5E2ZXFNCSWYL3KC/action/replication_record"}},"created_at":"2026-05-18T00:01:48.371357+00:00","updated_at":"2026-05-18T00:01:48.371357+00:00"}