{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:J4EPQ3A3NGNOQDTJKASS6KNTYL","short_pith_number":"pith:J4EPQ3A3","schema_version":"1.0","canonical_sha256":"4f08f86c1b699ae80e6950252f29b3c2f919b06207846b1d335a03bceb89c95b","source":{"kind":"arxiv","id":"1909.01311","version":2},"attestation_state":"computed","paper":{"title":"Learning without feedback: Fixed random learning signals allow for feedforward training of deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Charlotte Frenkel, David Bol, Martin Lefebvre","submitted_at":"2019-09-03T17:04:00Z","abstract_excerpt":"While the backpropagation of error algorithm enables deep neural network training, it implies (i) bidirectional synaptic weight transport and (ii) update locking until the forward and backward passes are completed. Not only do these constraints preclude biological plausibility, but they also hinder the development of low-cost adaptive smart sensors at the edge, as they severely constrain memory accesses and entail buffering overhead. In this work, we show that the one-hot-encoded labels provided in supervised classification problems, denoted as targets, can be viewed as a proxy for the error s"},"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":"1909.01311","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-03T17:04:00Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"3fd25b82064427ae774882342012bc1772905a08ea06b5e6ac69cee7d7495b0d","abstract_canon_sha256":"b94b327df9eac932a60ca60baf33f50c98ed2a13dd85c6ea73defa97bd010ea8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:07:13.123671Z","signature_b64":"UpeQf6K8kiSoTZhm/Eg6LquVgjcUszJV2YwB8L+QEhmuentGbcenfz9xG7bC9cxR+h3dEzREhX0LKrJ8TF1pCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f08f86c1b699ae80e6950252f29b3c2f919b06207846b1d335a03bceb89c95b","last_reissued_at":"2026-07-05T02:07:13.123204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:07:13.123204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning without feedback: Fixed random learning signals allow for feedforward training of deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Charlotte Frenkel, David Bol, Martin Lefebvre","submitted_at":"2019-09-03T17:04:00Z","abstract_excerpt":"While the backpropagation of error algorithm enables deep neural network training, it implies (i) bidirectional synaptic weight transport and (ii) update locking until the forward and backward passes are completed. Not only do these constraints preclude biological plausibility, but they also hinder the development of low-cost adaptive smart sensors at the edge, as they severely constrain memory accesses and entail buffering overhead. In this work, we show that the one-hot-encoded labels provided in supervised classification problems, denoted as targets, can be viewed as a proxy for the error s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01311","kind":"arxiv","version":2},"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/1909.01311/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":"1909.01311","created_at":"2026-07-05T02:07:13.123262+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.01311v2","created_at":"2026-07-05T02:07:13.123262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01311","created_at":"2026-07-05T02:07:13.123262+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4EPQ3A3NGNO","created_at":"2026-07-05T02:07:13.123262+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4EPQ3A3NGNOQDTJ","created_at":"2026-07-05T02:07:13.123262+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4EPQ3A3","created_at":"2026-07-05T02:07:13.123262+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.08655","citing_title":"Spiking Neural Predictive Coding for Continual Learning from Data Streams","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J4EPQ3A3NGNOQDTJKASS6KNTYL","json":"https://pith.science/pith/J4EPQ3A3NGNOQDTJKASS6KNTYL.json","graph_json":"https://pith.science/api/pith-number/J4EPQ3A3NGNOQDTJKASS6KNTYL/graph.json","events_json":"https://pith.science/api/pith-number/J4EPQ3A3NGNOQDTJKASS6KNTYL/events.json","paper":"https://pith.science/paper/J4EPQ3A3"},"agent_actions":{"view_html":"https://pith.science/pith/J4EPQ3A3NGNOQDTJKASS6KNTYL","download_json":"https://pith.science/pith/J4EPQ3A3NGNOQDTJKASS6KNTYL.json","view_paper":"https://pith.science/paper/J4EPQ3A3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.01311&json=true","fetch_graph":"https://pith.science/api/pith-number/J4EPQ3A3NGNOQDTJKASS6KNTYL/graph.json","fetch_events":"https://pith.science/api/pith-number/J4EPQ3A3NGNOQDTJKASS6KNTYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4EPQ3A3NGNOQDTJKASS6KNTYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4EPQ3A3NGNOQDTJKASS6KNTYL/action/storage_attestation","attest_author":"https://pith.science/pith/J4EPQ3A3NGNOQDTJKASS6KNTYL/action/author_attestation","sign_citation":"https://pith.science/pith/J4EPQ3A3NGNOQDTJKASS6KNTYL/action/citation_signature","submit_replication":"https://pith.science/pith/J4EPQ3A3NGNOQDTJKASS6KNTYL/action/replication_record"}},"created_at":"2026-07-05T02:07:13.123262+00:00","updated_at":"2026-07-05T02:07:13.123262+00:00"}