{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G4627R6PJVYSF74FOWCRL5T4N4","short_pith_number":"pith:G4627R6P","schema_version":"1.0","canonical_sha256":"373dafc7cf4d7122ff85758515f67c6f308e53da0f3fcc8e93ce469e8316c657","source":{"kind":"arxiv","id":"2403.00270","version":1},"attestation_state":"computed","paper":{"title":"Event-Driven Learning for Spiking Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.NE","authors_text":"Ammar Belatreche, Haizhou Li, Hong Chen, Jibin Wu, Jilin Zhang, Malu Zhang, Wenjie Wei, Xuerui Qiu, Yang Yang, Zijing Xu","submitted_at":"2024-03-01T04:17:59Z","abstract_excerpt":"Brain-inspired spiking neural networks (SNNs) have gained prominence in the field of neuromorphic computing owing to their low energy consumption during feedforward inference on neuromorphic hardware. However, it remains an open challenge how to effectively benefit from the sparse event-driven property of SNNs to minimize backpropagation learning costs. In this paper, we conduct a comprehensive examination of the existing event-driven learning algorithms, reveal their limitations, and propose novel solutions to overcome them. Specifically, we introduce two novel event-driven learning methods: "},"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":"2403.00270","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2024-03-01T04:17:59Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"db1d14a9ab2883e32184f04e8eed0f0589837d509dd92c965dab8fb720dd6e0b","abstract_canon_sha256":"1e24030048eceb03adef4e9fd41f24c628ecab9701e1d6ff7251b051a785fb22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:01.736061Z","signature_b64":"XZ/tMG2Zpc9Gf08/23+VRBAcViCS02Poqp0HR1SiV+U6ecVWC4r2sJHDAK9wKZDbYaSteo5o9aZa/mj4i1ivBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"373dafc7cf4d7122ff85758515f67c6f308e53da0f3fcc8e93ce469e8316c657","last_reissued_at":"2026-07-05T07:51:01.735588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:01.735588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Event-Driven Learning for Spiking Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.NE","authors_text":"Ammar Belatreche, Haizhou Li, Hong Chen, Jibin Wu, Jilin Zhang, Malu Zhang, Wenjie Wei, Xuerui Qiu, Yang Yang, Zijing Xu","submitted_at":"2024-03-01T04:17:59Z","abstract_excerpt":"Brain-inspired spiking neural networks (SNNs) have gained prominence in the field of neuromorphic computing owing to their low energy consumption during feedforward inference on neuromorphic hardware. However, it remains an open challenge how to effectively benefit from the sparse event-driven property of SNNs to minimize backpropagation learning costs. In this paper, we conduct a comprehensive examination of the existing event-driven learning algorithms, reveal their limitations, and propose novel solutions to overcome them. Specifically, we introduce two novel event-driven learning methods: "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00270","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.00270/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":"2403.00270","created_at":"2026-07-05T07:51:01.735656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00270v1","created_at":"2026-07-05T07:51:01.735656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00270","created_at":"2026-07-05T07:51:01.735656+00:00"},{"alias_kind":"pith_short_12","alias_value":"G4627R6PJVYS","created_at":"2026-07-05T07:51:01.735656+00:00"},{"alias_kind":"pith_short_16","alias_value":"G4627R6PJVYSF74F","created_at":"2026-07-05T07:51:01.735656+00:00"},{"alias_kind":"pith_short_8","alias_value":"G4627R6P","created_at":"2026-07-05T07:51:01.735656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01945","citing_title":"Beyond Low-Rank: Low-Rank Sparse Prompting via Spiking Neural Network and Prompt Factorization","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2409.08290","citing_title":"Representation Capacity-Matched QNN-SNN Twin Construction for Rate-Encoded SNNs","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G4627R6PJVYSF74FOWCRL5T4N4","json":"https://pith.science/pith/G4627R6PJVYSF74FOWCRL5T4N4.json","graph_json":"https://pith.science/api/pith-number/G4627R6PJVYSF74FOWCRL5T4N4/graph.json","events_json":"https://pith.science/api/pith-number/G4627R6PJVYSF74FOWCRL5T4N4/events.json","paper":"https://pith.science/paper/G4627R6P"},"agent_actions":{"view_html":"https://pith.science/pith/G4627R6PJVYSF74FOWCRL5T4N4","download_json":"https://pith.science/pith/G4627R6PJVYSF74FOWCRL5T4N4.json","view_paper":"https://pith.science/paper/G4627R6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00270&json=true","fetch_graph":"https://pith.science/api/pith-number/G4627R6PJVYSF74FOWCRL5T4N4/graph.json","fetch_events":"https://pith.science/api/pith-number/G4627R6PJVYSF74FOWCRL5T4N4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G4627R6PJVYSF74FOWCRL5T4N4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G4627R6PJVYSF74FOWCRL5T4N4/action/storage_attestation","attest_author":"https://pith.science/pith/G4627R6PJVYSF74FOWCRL5T4N4/action/author_attestation","sign_citation":"https://pith.science/pith/G4627R6PJVYSF74FOWCRL5T4N4/action/citation_signature","submit_replication":"https://pith.science/pith/G4627R6PJVYSF74FOWCRL5T4N4/action/replication_record"}},"created_at":"2026-07-05T07:51:01.735656+00:00","updated_at":"2026-07-05T07:51:01.735656+00:00"}