{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:PT4YRQBANZP6JQVWIRWCYO46N4","short_pith_number":"pith:PT4YRQBA","schema_version":"1.0","canonical_sha256":"7cf988c0206e5fe4c2b6446c2c3b9e6f04e926f8e54466009ede22749574a98b","source":{"kind":"arxiv","id":"1510.01624","version":4},"attestation_state":"computed","paper":{"title":"Population-Contrastive-Divergence: Does Consistency help with RBM training?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Asja Fischer, Christian Igel, Oswin Krause","submitted_at":"2015-10-06T15:29:04Z","abstract_excerpt":"Estimating the log-likelihood gradient with respect to the parameters of a Restricted Boltzmann Machine (RBM) typically requires sampling using Markov Chain Monte Carlo (MCMC) techniques. To save computation time, the Markov chains are only run for a small number of steps, which leads to a biased estimate. This bias can cause RBM training algorithms such as Contrastive Divergence (CD) learning to deteriorate. We adopt the idea behind Population Monte Carlo (PMC) methods to devise a new RBM training algorithm termed Population-Contrastive-Divergence (pop-CD). Compared to CD, it leads to a consi"},"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":"1510.01624","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-10-06T15:29:04Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"6881fe11df90e702a83a5e8724574d2e677a04a7b7ad1d4754395b281a55a9b9","abstract_canon_sha256":"deb69fae361147c63578d1b09db1d312f4127327f86b9017c73f5abe2e191c5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:23.345077Z","signature_b64":"qNZtmkC876btJPXiQ2gYdRohcDx6TBrzAEV/3GNVMl7nKXurceCppu/vx7aIxyScT84Qt9d267zxI6LLM/fsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cf988c0206e5fe4c2b6446c2c3b9e6f04e926f8e54466009ede22749574a98b","last_reissued_at":"2026-05-18T00:41:23.344601Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:23.344601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Population-Contrastive-Divergence: Does Consistency help with RBM training?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Asja Fischer, Christian Igel, Oswin Krause","submitted_at":"2015-10-06T15:29:04Z","abstract_excerpt":"Estimating the log-likelihood gradient with respect to the parameters of a Restricted Boltzmann Machine (RBM) typically requires sampling using Markov Chain Monte Carlo (MCMC) techniques. To save computation time, the Markov chains are only run for a small number of steps, which leads to a biased estimate. This bias can cause RBM training algorithms such as Contrastive Divergence (CD) learning to deteriorate. We adopt the idea behind Population Monte Carlo (PMC) methods to devise a new RBM training algorithm termed Population-Contrastive-Divergence (pop-CD). Compared to CD, it leads to a consi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.01624","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1510.01624","created_at":"2026-05-18T00:41:23.344666+00:00"},{"alias_kind":"arxiv_version","alias_value":"1510.01624v4","created_at":"2026-05-18T00:41:23.344666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.01624","created_at":"2026-05-18T00:41:23.344666+00:00"},{"alias_kind":"pith_short_12","alias_value":"PT4YRQBANZP6","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_16","alias_value":"PT4YRQBANZP6JQVW","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_8","alias_value":"PT4YRQBA","created_at":"2026-05-18T12:29:37.295048+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/PT4YRQBANZP6JQVWIRWCYO46N4","json":"https://pith.science/pith/PT4YRQBANZP6JQVWIRWCYO46N4.json","graph_json":"https://pith.science/api/pith-number/PT4YRQBANZP6JQVWIRWCYO46N4/graph.json","events_json":"https://pith.science/api/pith-number/PT4YRQBANZP6JQVWIRWCYO46N4/events.json","paper":"https://pith.science/paper/PT4YRQBA"},"agent_actions":{"view_html":"https://pith.science/pith/PT4YRQBANZP6JQVWIRWCYO46N4","download_json":"https://pith.science/pith/PT4YRQBANZP6JQVWIRWCYO46N4.json","view_paper":"https://pith.science/paper/PT4YRQBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1510.01624&json=true","fetch_graph":"https://pith.science/api/pith-number/PT4YRQBANZP6JQVWIRWCYO46N4/graph.json","fetch_events":"https://pith.science/api/pith-number/PT4YRQBANZP6JQVWIRWCYO46N4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PT4YRQBANZP6JQVWIRWCYO46N4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PT4YRQBANZP6JQVWIRWCYO46N4/action/storage_attestation","attest_author":"https://pith.science/pith/PT4YRQBANZP6JQVWIRWCYO46N4/action/author_attestation","sign_citation":"https://pith.science/pith/PT4YRQBANZP6JQVWIRWCYO46N4/action/citation_signature","submit_replication":"https://pith.science/pith/PT4YRQBANZP6JQVWIRWCYO46N4/action/replication_record"}},"created_at":"2026-05-18T00:41:23.344666+00:00","updated_at":"2026-05-18T00:41:23.344666+00:00"}