{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:CC74K3EO6K7BNDFAZKSP5P3X5V","short_pith_number":"pith:CC74K3EO","schema_version":"1.0","canonical_sha256":"10bfc56c8ef2be168ca0caa4febf77ed6b76cee31e9d61b577fa809971cb0010","source":{"kind":"arxiv","id":"1701.07148","version":1},"attestation_state":"computed","paper":{"title":"CP-decomposition with Tensor Power Method for Convolutional Neural Networks Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Marcella Astrid, Seung-Ik Lee","submitted_at":"2017-01-25T02:58:06Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) has shown a great success in many areas including complex image classification tasks. However, they need a lot of memory and computational cost, which hinders them from running in relatively low-end smart devices such as smart phones. We propose a CNN compression method based on CP-decomposition and Tensor Power Method. We also propose an iterative fine tuning, with which we fine-tune the whole network after decomposing each layer, but before decomposing the next layer. Significant reduction in memory and computation cost is achieved compared to state-of-th"},"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":"1701.07148","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-25T02:58:06Z","cross_cats_sorted":[],"title_canon_sha256":"e7b67232b642d06933c528336658229465125fa2975fd15ffd2a900d52fe1d0b","abstract_canon_sha256":"4ce1d7a017b08eae209dae287d5bd931214f95edf7fec13300428bed482c8b0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:07.367192Z","signature_b64":"ajGzCH+M0CLlKcLfN+0li0x277531jy6VP8zfv3Y7wqkYK1GjpZKRDe63iw7pNpdLSOV+M/71uTK2qAD6A1PCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10bfc56c8ef2be168ca0caa4febf77ed6b76cee31e9d61b577fa809971cb0010","last_reissued_at":"2026-05-18T00:52:07.366708Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:07.366708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CP-decomposition with Tensor Power Method for Convolutional Neural Networks Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Marcella Astrid, Seung-Ik Lee","submitted_at":"2017-01-25T02:58:06Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) has shown a great success in many areas including complex image classification tasks. However, they need a lot of memory and computational cost, which hinders them from running in relatively low-end smart devices such as smart phones. We propose a CNN compression method based on CP-decomposition and Tensor Power Method. We also propose an iterative fine tuning, with which we fine-tune the whole network after decomposing each layer, but before decomposing the next layer. Significant reduction in memory and computation cost is achieved compared to state-of-th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.07148","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":"1701.07148","created_at":"2026-05-18T00:52:07.366783+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.07148v1","created_at":"2026-05-18T00:52:07.366783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.07148","created_at":"2026-05-18T00:52:07.366783+00:00"},{"alias_kind":"pith_short_12","alias_value":"CC74K3EO6K7B","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"CC74K3EO6K7BNDFA","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"CC74K3EO","created_at":"2026-05-18T12:31:10.602751+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/CC74K3EO6K7BNDFAZKSP5P3X5V","json":"https://pith.science/pith/CC74K3EO6K7BNDFAZKSP5P3X5V.json","graph_json":"https://pith.science/api/pith-number/CC74K3EO6K7BNDFAZKSP5P3X5V/graph.json","events_json":"https://pith.science/api/pith-number/CC74K3EO6K7BNDFAZKSP5P3X5V/events.json","paper":"https://pith.science/paper/CC74K3EO"},"agent_actions":{"view_html":"https://pith.science/pith/CC74K3EO6K7BNDFAZKSP5P3X5V","download_json":"https://pith.science/pith/CC74K3EO6K7BNDFAZKSP5P3X5V.json","view_paper":"https://pith.science/paper/CC74K3EO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.07148&json=true","fetch_graph":"https://pith.science/api/pith-number/CC74K3EO6K7BNDFAZKSP5P3X5V/graph.json","fetch_events":"https://pith.science/api/pith-number/CC74K3EO6K7BNDFAZKSP5P3X5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CC74K3EO6K7BNDFAZKSP5P3X5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CC74K3EO6K7BNDFAZKSP5P3X5V/action/storage_attestation","attest_author":"https://pith.science/pith/CC74K3EO6K7BNDFAZKSP5P3X5V/action/author_attestation","sign_citation":"https://pith.science/pith/CC74K3EO6K7BNDFAZKSP5P3X5V/action/citation_signature","submit_replication":"https://pith.science/pith/CC74K3EO6K7BNDFAZKSP5P3X5V/action/replication_record"}},"created_at":"2026-05-18T00:52:07.366783+00:00","updated_at":"2026-05-18T00:52:07.366783+00:00"}