{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:234ZUZQERVEMFMZTNQKLVRRTIA","short_pith_number":"pith:234ZUZQE","schema_version":"1.0","canonical_sha256":"d6f99a66048d48c2b3336c14bac633400d61eb10dec0271f231722572e5306f9","source":{"kind":"arxiv","id":"1812.11337","version":1},"attestation_state":"computed","paper":{"title":"Quantized Guided Pruning for Efficient Hardware Implementations of Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Ghouthi Boukli Hacene (ELEC), Matthieu Arzel (ELEC), Nicolas Farrugia (ELEC), Vincent Gripon, Yoshua Bengio (DIRO)","submitted_at":"2018-12-29T11:06:39Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) are state-of-the-art in numerous computer vision tasks such as object classification and detection. However, the large amount of parameters they contain leads to a high computational complexity and strongly limits their usability in budget-constrained devices such as embedded devices. In this paper, we propose a combination of a new pruning technique and a quantization scheme that effectively reduce the complexity and memory usage of convolutional layers of CNNs, and replace the complex convolutional operation by a low-cost multiplexer. We perform experimen"},"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":"1812.11337","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-29T11:06:39Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"c15d142280913cddc79055a57a746a2733e89cce78322eeb3c83535543e0a893","abstract_canon_sha256":"0861d7f0136e42ecf4d9f9d74c1e8d507ad9f884b2f443cabd83621611061f82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:12.207811Z","signature_b64":"Z2iwx/r0hw99MXqpjV7GapSe0Y1YQFv3fLm5EQnjuE8RwRzwygIlqUpZNqFChioINEMEI+LUbQnX5ECcZHpvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6f99a66048d48c2b3336c14bac633400d61eb10dec0271f231722572e5306f9","last_reissued_at":"2026-05-17T23:57:12.207447Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:12.207447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantized Guided Pruning for Efficient Hardware Implementations of Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Ghouthi Boukli Hacene (ELEC), Matthieu Arzel (ELEC), Nicolas Farrugia (ELEC), Vincent Gripon, Yoshua Bengio (DIRO)","submitted_at":"2018-12-29T11:06:39Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) are state-of-the-art in numerous computer vision tasks such as object classification and detection. However, the large amount of parameters they contain leads to a high computational complexity and strongly limits their usability in budget-constrained devices such as embedded devices. In this paper, we propose a combination of a new pruning technique and a quantization scheme that effectively reduce the complexity and memory usage of convolutional layers of CNNs, and replace the complex convolutional operation by a low-cost multiplexer. We perform experimen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.11337","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":"1812.11337","created_at":"2026-05-17T23:57:12.207504+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.11337v1","created_at":"2026-05-17T23:57:12.207504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.11337","created_at":"2026-05-17T23:57:12.207504+00:00"},{"alias_kind":"pith_short_12","alias_value":"234ZUZQERVEM","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"234ZUZQERVEMFMZT","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"234ZUZQE","created_at":"2026-05-18T12:31:59.375834+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/234ZUZQERVEMFMZTNQKLVRRTIA","json":"https://pith.science/pith/234ZUZQERVEMFMZTNQKLVRRTIA.json","graph_json":"https://pith.science/api/pith-number/234ZUZQERVEMFMZTNQKLVRRTIA/graph.json","events_json":"https://pith.science/api/pith-number/234ZUZQERVEMFMZTNQKLVRRTIA/events.json","paper":"https://pith.science/paper/234ZUZQE"},"agent_actions":{"view_html":"https://pith.science/pith/234ZUZQERVEMFMZTNQKLVRRTIA","download_json":"https://pith.science/pith/234ZUZQERVEMFMZTNQKLVRRTIA.json","view_paper":"https://pith.science/paper/234ZUZQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.11337&json=true","fetch_graph":"https://pith.science/api/pith-number/234ZUZQERVEMFMZTNQKLVRRTIA/graph.json","fetch_events":"https://pith.science/api/pith-number/234ZUZQERVEMFMZTNQKLVRRTIA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/234ZUZQERVEMFMZTNQKLVRRTIA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/234ZUZQERVEMFMZTNQKLVRRTIA/action/storage_attestation","attest_author":"https://pith.science/pith/234ZUZQERVEMFMZTNQKLVRRTIA/action/author_attestation","sign_citation":"https://pith.science/pith/234ZUZQERVEMFMZTNQKLVRRTIA/action/citation_signature","submit_replication":"https://pith.science/pith/234ZUZQERVEMFMZTNQKLVRRTIA/action/replication_record"}},"created_at":"2026-05-17T23:57:12.207504+00:00","updated_at":"2026-05-17T23:57:12.207504+00:00"}