{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2M2NMMRIQGWXTDD5GGEVSYUPST","short_pith_number":"pith:2M2NMMRI","schema_version":"1.0","canonical_sha256":"d334d6322881ad798c7d318959628f94dd8a0ab8b45e605fd81f16f8a987aee5","source":{"kind":"arxiv","id":"2001.01969","version":3},"attestation_state":"computed","paper":{"title":"Sparse Weight Activation Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Md Aamir Raihan, Tor M. Aamodt","submitted_at":"2020-01-07T11:08:13Z","abstract_excerpt":"Neural network training is computationally and memory intensive. Sparse training can reduce the burden on emerging hardware platforms designed to accelerate sparse computations, but it can affect network convergence. In this work, we propose a novel CNN training algorithm Sparse Weight Activation Training (SWAT). SWAT is more computation and memory-efficient than conventional training. SWAT modifies back-propagation based on the empirical insight that convergence during training tends to be robust to the elimination of (i) small magnitude weights during the forward pass and (ii) both small mag"},"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":"2001.01969","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-07T11:08:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d3452da1ecce3443e7f0154852e32f2bfb89f50a8d665679a2b868d3a7882e14","abstract_canon_sha256":"f325fa221e7baeb2cee5add917580059b342c83f0b79df28728503dce31c32bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:07.534423Z","signature_b64":"Z59P2En51W0rNkPW0XsUYDoQGFNsebbNyviqH3E5a0TtKcpCeYBmKlEVzi0MezM+8YJufu2yIc4O13MaJ8COCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d334d6322881ad798c7d318959628f94dd8a0ab8b45e605fd81f16f8a987aee5","last_reissued_at":"2026-07-05T01:48:07.534005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:07.534005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse Weight Activation Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Md Aamir Raihan, Tor M. Aamodt","submitted_at":"2020-01-07T11:08:13Z","abstract_excerpt":"Neural network training is computationally and memory intensive. Sparse training can reduce the burden on emerging hardware platforms designed to accelerate sparse computations, but it can affect network convergence. In this work, we propose a novel CNN training algorithm Sparse Weight Activation Training (SWAT). SWAT is more computation and memory-efficient than conventional training. SWAT modifies back-propagation based on the empirical insight that convergence during training tends to be robust to the elimination of (i) small magnitude weights during the forward pass and (ii) both small mag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.01969","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2001.01969/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2001.01969","created_at":"2026-07-05T01:48:07.534068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.01969v3","created_at":"2026-07-05T01:48:07.534068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.01969","created_at":"2026-07-05T01:48:07.534068+00:00"},{"alias_kind":"pith_short_12","alias_value":"2M2NMMRIQGWX","created_at":"2026-07-05T01:48:07.534068+00:00"},{"alias_kind":"pith_short_16","alias_value":"2M2NMMRIQGWXTDD5","created_at":"2026-07-05T01:48:07.534068+00:00"},{"alias_kind":"pith_short_8","alias_value":"2M2NMMRI","created_at":"2026-07-05T01:48:07.534068+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/2M2NMMRIQGWXTDD5GGEVSYUPST","json":"https://pith.science/pith/2M2NMMRIQGWXTDD5GGEVSYUPST.json","graph_json":"https://pith.science/api/pith-number/2M2NMMRIQGWXTDD5GGEVSYUPST/graph.json","events_json":"https://pith.science/api/pith-number/2M2NMMRIQGWXTDD5GGEVSYUPST/events.json","paper":"https://pith.science/paper/2M2NMMRI"},"agent_actions":{"view_html":"https://pith.science/pith/2M2NMMRIQGWXTDD5GGEVSYUPST","download_json":"https://pith.science/pith/2M2NMMRIQGWXTDD5GGEVSYUPST.json","view_paper":"https://pith.science/paper/2M2NMMRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.01969&json=true","fetch_graph":"https://pith.science/api/pith-number/2M2NMMRIQGWXTDD5GGEVSYUPST/graph.json","fetch_events":"https://pith.science/api/pith-number/2M2NMMRIQGWXTDD5GGEVSYUPST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2M2NMMRIQGWXTDD5GGEVSYUPST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2M2NMMRIQGWXTDD5GGEVSYUPST/action/storage_attestation","attest_author":"https://pith.science/pith/2M2NMMRIQGWXTDD5GGEVSYUPST/action/author_attestation","sign_citation":"https://pith.science/pith/2M2NMMRIQGWXTDD5GGEVSYUPST/action/citation_signature","submit_replication":"https://pith.science/pith/2M2NMMRIQGWXTDD5GGEVSYUPST/action/replication_record"}},"created_at":"2026-07-05T01:48:07.534068+00:00","updated_at":"2026-07-05T01:48:07.534068+00:00"}