{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LXZUZU6GN3Z65DK6GSOLON6XO3","short_pith_number":"pith:LXZUZU6G","schema_version":"1.0","canonical_sha256":"5df34cd3c66ef3ee8d5e349cb737d776d19e71ab84520e5fa53a821d886e029c","source":{"kind":"arxiv","id":"2412.18349","version":1},"attestation_state":"computed","paper":{"title":"Neural auto-association with optimal Bayesian learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Andreas Knoblauch","submitted_at":"2024-12-24T11:22:18Z","abstract_excerpt":"Neural associative memories are single layer perceptrons with fast synaptic learning typically storing discrete associations between pairs of neural activity patterns. Previous works have analyzed the optimal networks under naive Bayes assumptions of independent pattern components and heteroassociation, where the task is to learn associations from input to output patterns. Here I study the optimal Bayesian associative network for auto-association where input and output layers are identical. In particular, I compare performance to different variants of approximate Bayesian learning rules, like "},"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":"2412.18349","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.NE","submitted_at":"2024-12-24T11:22:18Z","cross_cats_sorted":[],"title_canon_sha256":"4e7bf4bd24b1f82711ad7b556c4d1df8ec5332960187da9fc4150820455e1732","abstract_canon_sha256":"7361daa1309b42310755d44ad9e96acd9b9053900104be506436d939dd1d0cdb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:54.242545Z","signature_b64":"j4+Ht4mfSvfALu9pMucwq8IOdARWbQUGUEudEyafoToBUSoeNYrSm+NB+waYZ34K+NtW47TEWzKi/KtE9hiYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5df34cd3c66ef3ee8d5e349cb737d776d19e71ab84520e5fa53a821d886e029c","last_reissued_at":"2026-07-05T09:53:54.241953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:54.241953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural auto-association with optimal Bayesian learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Andreas Knoblauch","submitted_at":"2024-12-24T11:22:18Z","abstract_excerpt":"Neural associative memories are single layer perceptrons with fast synaptic learning typically storing discrete associations between pairs of neural activity patterns. Previous works have analyzed the optimal networks under naive Bayes assumptions of independent pattern components and heteroassociation, where the task is to learn associations from input to output patterns. Here I study the optimal Bayesian associative network for auto-association where input and output layers are identical. In particular, I compare performance to different variants of approximate Bayesian learning rules, like "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18349","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/2412.18349/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":"2412.18349","created_at":"2026-07-05T09:53:54.242013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18349v1","created_at":"2026-07-05T09:53:54.242013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18349","created_at":"2026-07-05T09:53:54.242013+00:00"},{"alias_kind":"pith_short_12","alias_value":"LXZUZU6GN3Z6","created_at":"2026-07-05T09:53:54.242013+00:00"},{"alias_kind":"pith_short_16","alias_value":"LXZUZU6GN3Z65DK6","created_at":"2026-07-05T09:53:54.242013+00:00"},{"alias_kind":"pith_short_8","alias_value":"LXZUZU6G","created_at":"2026-07-05T09:53:54.242013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29528","citing_title":"Supervised Hebbian learning in Deep Counterstream Associative Networks","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LXZUZU6GN3Z65DK6GSOLON6XO3","json":"https://pith.science/pith/LXZUZU6GN3Z65DK6GSOLON6XO3.json","graph_json":"https://pith.science/api/pith-number/LXZUZU6GN3Z65DK6GSOLON6XO3/graph.json","events_json":"https://pith.science/api/pith-number/LXZUZU6GN3Z65DK6GSOLON6XO3/events.json","paper":"https://pith.science/paper/LXZUZU6G"},"agent_actions":{"view_html":"https://pith.science/pith/LXZUZU6GN3Z65DK6GSOLON6XO3","download_json":"https://pith.science/pith/LXZUZU6GN3Z65DK6GSOLON6XO3.json","view_paper":"https://pith.science/paper/LXZUZU6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18349&json=true","fetch_graph":"https://pith.science/api/pith-number/LXZUZU6GN3Z65DK6GSOLON6XO3/graph.json","fetch_events":"https://pith.science/api/pith-number/LXZUZU6GN3Z65DK6GSOLON6XO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LXZUZU6GN3Z65DK6GSOLON6XO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LXZUZU6GN3Z65DK6GSOLON6XO3/action/storage_attestation","attest_author":"https://pith.science/pith/LXZUZU6GN3Z65DK6GSOLON6XO3/action/author_attestation","sign_citation":"https://pith.science/pith/LXZUZU6GN3Z65DK6GSOLON6XO3/action/citation_signature","submit_replication":"https://pith.science/pith/LXZUZU6GN3Z65DK6GSOLON6XO3/action/replication_record"}},"created_at":"2026-07-05T09:53:54.242013+00:00","updated_at":"2026-07-05T09:53:54.242013+00:00"}