{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:LOPAUYUEAWPTMJ37MM2FGA2A7C","short_pith_number":"pith:LOPAUYUE","schema_version":"1.0","canonical_sha256":"5b9e0a6284059f36277f6334530340f8a0b1d7b37769914375ebd02011c54808","source":{"kind":"arxiv","id":"1510.06356","version":1},"attestation_state":"computed","paper":{"title":"Application of Quantum Annealing to Training of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"quant-ph","authors_text":"Maxwell P. Henderson, Steven H. Adachi","submitted_at":"2015-10-21T18:21:39Z","abstract_excerpt":"In Deep Learning, a well-known approach for training a Deep Neural Network starts by training a generative Deep Belief Network model, typically using Contrastive Divergence (CD), then fine-tuning the weights using backpropagation or other discriminative techniques. However, the generative training can be time-consuming due to the slow mixing of Gibbs sampling. We investigated an alternative approach that estimates model expectations of Restricted Boltzmann Machines using samples from a D-Wave quantum annealing machine. We tested this method on a coarse-grained version of the MNIST data set. In"},"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":"1510.06356","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2015-10-21T18:21:39Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"98221a8342e85503d951094d324eae027fc73faeb35a075b466320b89df6eabf","abstract_canon_sha256":"fe90dc706d758a999f048ee8c44b8f215d6bda185ae612baa99a8a0c1615cc17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:29:37.149485Z","signature_b64":"jSqZnBrffNlxlislTeyepdMXyvhx7w2D8mRmJLOLQro2kzhBYyNlsJpyDr6Bp9DNNQKnlxIJiKpiyG7RZB6QCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b9e0a6284059f36277f6334530340f8a0b1d7b37769914375ebd02011c54808","last_reissued_at":"2026-05-18T01:29:37.148896Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:29:37.148896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Application of Quantum Annealing to Training of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"quant-ph","authors_text":"Maxwell P. Henderson, Steven H. Adachi","submitted_at":"2015-10-21T18:21:39Z","abstract_excerpt":"In Deep Learning, a well-known approach for training a Deep Neural Network starts by training a generative Deep Belief Network model, typically using Contrastive Divergence (CD), then fine-tuning the weights using backpropagation or other discriminative techniques. However, the generative training can be time-consuming due to the slow mixing of Gibbs sampling. We investigated an alternative approach that estimates model expectations of Restricted Boltzmann Machines using samples from a D-Wave quantum annealing machine. We tested this method on a coarse-grained version of the MNIST data set. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.06356","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":""},"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":"1510.06356","created_at":"2026-05-18T01:29:37.148982+00:00"},{"alias_kind":"arxiv_version","alias_value":"1510.06356v1","created_at":"2026-05-18T01:29:37.148982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.06356","created_at":"2026-05-18T01:29:37.148982+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOPAUYUEAWPT","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOPAUYUEAWPTMJ37","created_at":"2026-05-18T12:29:29.992203+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOPAUYUE","created_at":"2026-05-18T12:29:29.992203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2409.18126","citing_title":"Boltzmann Sampling by Diabatic Quantum Annealing","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2507.10722","citing_title":"Bridging Brains and Machines: A Unified Frontier in Neuroscience, Artificial Intelligence, and Neuromorphic Systems","ref_index":249,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09032","citing_title":"A Quantum Inspired Variational Kernel and Explainable AI Framework for Cross Region Solar and Wind Energy Forecasting","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06857","citing_title":"Quantum Annealing: Optimisation, Sampling, and Many-Body Dynamics","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LOPAUYUEAWPTMJ37MM2FGA2A7C","json":"https://pith.science/pith/LOPAUYUEAWPTMJ37MM2FGA2A7C.json","graph_json":"https://pith.science/api/pith-number/LOPAUYUEAWPTMJ37MM2FGA2A7C/graph.json","events_json":"https://pith.science/api/pith-number/LOPAUYUEAWPTMJ37MM2FGA2A7C/events.json","paper":"https://pith.science/paper/LOPAUYUE"},"agent_actions":{"view_html":"https://pith.science/pith/LOPAUYUEAWPTMJ37MM2FGA2A7C","download_json":"https://pith.science/pith/LOPAUYUEAWPTMJ37MM2FGA2A7C.json","view_paper":"https://pith.science/paper/LOPAUYUE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1510.06356&json=true","fetch_graph":"https://pith.science/api/pith-number/LOPAUYUEAWPTMJ37MM2FGA2A7C/graph.json","fetch_events":"https://pith.science/api/pith-number/LOPAUYUEAWPTMJ37MM2FGA2A7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOPAUYUEAWPTMJ37MM2FGA2A7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOPAUYUEAWPTMJ37MM2FGA2A7C/action/storage_attestation","attest_author":"https://pith.science/pith/LOPAUYUEAWPTMJ37MM2FGA2A7C/action/author_attestation","sign_citation":"https://pith.science/pith/LOPAUYUEAWPTMJ37MM2FGA2A7C/action/citation_signature","submit_replication":"https://pith.science/pith/LOPAUYUEAWPTMJ37MM2FGA2A7C/action/replication_record"}},"created_at":"2026-05-18T01:29:37.148982+00:00","updated_at":"2026-05-18T01:29:37.148982+00:00"}