{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VXNNKF6YD5PJFF5WOBO562RIEU","short_pith_number":"pith:VXNNKF6Y","schema_version":"1.0","canonical_sha256":"addad517d81f5e9297b6705ddf6a28251a4f8fc9e4d020fcf217a60fb4db8e89","source":{"kind":"arxiv","id":"2006.04436","version":1},"attestation_state":"computed","paper":{"title":"Training Deep Spiking Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.NE","authors_text":"(2) SRI International, Alfonsas Jur\\v{s}\\.enas (1), Eimantas Ledinauskas (1), Giedrius Bura\\v{c}as (2) ((1) Baltic Institute of Advanced Technology, Julius Ruseckas (1), Lithuania, USA)","submitted_at":"2020-06-08T09:47:05Z","abstract_excerpt":"Computation using brain-inspired spiking neural networks (SNNs) with neuromorphic hardware may offer orders of magnitude higher energy efficiency compared to the current analog neural networks (ANNs). Unfortunately, training SNNs with the same number of layers as state of the art ANNs remains a challenge. To our knowledge the only method which is successful in this regard is supervised training of ANN and then converting it to SNN. In this work we directly train deep SNNs using backpropagation with surrogate gradient and find that due to implicitly recurrent nature of feed forward SNN's the ex"},"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":"2006.04436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2020-06-08T09:47:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1a60c98aed105e00e69b0ce3e322d5dec35d5bd12545d8be11beb9132cb34ad4","abstract_canon_sha256":"702b088714d7a8f9e81701a6be787f7ed2f1d09e3cb19e4cd28e2e611bb6b683"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:39.234430Z","signature_b64":"C+ImxCVBlNwY/q3QSuKBtZzl3kFzL71nCPibA/CLw4BYKujyxeKoYIOpLl78n4ZH4w8oEquV4EvLJVAtrfN+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"addad517d81f5e9297b6705ddf6a28251a4f8fc9e4d020fcf217a60fb4db8e89","last_reissued_at":"2026-07-05T01:08:39.233960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:39.233960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Deep Spiking Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.NE","authors_text":"(2) SRI International, Alfonsas Jur\\v{s}\\.enas (1), Eimantas Ledinauskas (1), Giedrius Bura\\v{c}as (2) ((1) Baltic Institute of Advanced Technology, Julius Ruseckas (1), Lithuania, USA)","submitted_at":"2020-06-08T09:47:05Z","abstract_excerpt":"Computation using brain-inspired spiking neural networks (SNNs) with neuromorphic hardware may offer orders of magnitude higher energy efficiency compared to the current analog neural networks (ANNs). Unfortunately, training SNNs with the same number of layers as state of the art ANNs remains a challenge. To our knowledge the only method which is successful in this regard is supervised training of ANN and then converting it to SNN. In this work we directly train deep SNNs using backpropagation with surrogate gradient and find that due to implicitly recurrent nature of feed forward SNN's the ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04436","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/2006.04436/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":"2006.04436","created_at":"2026-07-05T01:08:39.234020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.04436v1","created_at":"2026-07-05T01:08:39.234020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04436","created_at":"2026-07-05T01:08:39.234020+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXNNKF6YD5PJ","created_at":"2026-07-05T01:08:39.234020+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXNNKF6YD5PJFF5W","created_at":"2026-07-05T01:08:39.234020+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXNNKF6Y","created_at":"2026-07-05T01:08:39.234020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18250","citing_title":"IKUN: Initialization to Keep snn training and generalization great with sUrrogate-stable variaNce","ref_index":2002,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VXNNKF6YD5PJFF5WOBO562RIEU","json":"https://pith.science/pith/VXNNKF6YD5PJFF5WOBO562RIEU.json","graph_json":"https://pith.science/api/pith-number/VXNNKF6YD5PJFF5WOBO562RIEU/graph.json","events_json":"https://pith.science/api/pith-number/VXNNKF6YD5PJFF5WOBO562RIEU/events.json","paper":"https://pith.science/paper/VXNNKF6Y"},"agent_actions":{"view_html":"https://pith.science/pith/VXNNKF6YD5PJFF5WOBO562RIEU","download_json":"https://pith.science/pith/VXNNKF6YD5PJFF5WOBO562RIEU.json","view_paper":"https://pith.science/paper/VXNNKF6Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.04436&json=true","fetch_graph":"https://pith.science/api/pith-number/VXNNKF6YD5PJFF5WOBO562RIEU/graph.json","fetch_events":"https://pith.science/api/pith-number/VXNNKF6YD5PJFF5WOBO562RIEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXNNKF6YD5PJFF5WOBO562RIEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXNNKF6YD5PJFF5WOBO562RIEU/action/storage_attestation","attest_author":"https://pith.science/pith/VXNNKF6YD5PJFF5WOBO562RIEU/action/author_attestation","sign_citation":"https://pith.science/pith/VXNNKF6YD5PJFF5WOBO562RIEU/action/citation_signature","submit_replication":"https://pith.science/pith/VXNNKF6YD5PJFF5WOBO562RIEU/action/replication_record"}},"created_at":"2026-07-05T01:08:39.234020+00:00","updated_at":"2026-07-05T01:08:39.234020+00:00"}