{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:A6NMETRTPD377BXBVYWW66FK7P","short_pith_number":"pith:A6NMETRT","schema_version":"1.0","canonical_sha256":"079ac24e3378f7ff86e1ae2d6f78aafbd1d4c413013a3f06d66bcce29cf62879","source":{"kind":"arxiv","id":"1710.11052","version":1},"attestation_state":"computed","paper":{"title":"A Connection between Feed-Forward Neural Networks and Probabilistic Graphical Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Dmitrij Schlesinger","submitted_at":"2017-10-30T16:31:24Z","abstract_excerpt":"Two of the most popular modelling paradigms in computer vision are feed-forward neural networks (FFNs) and probabilistic graphical models (GMs). Various connections between the two have been studied in recent works, such as e.g. expressing mean-field based inference in a GM as an FFN. This paper establishes a new connection between FFNs and GMs. Our key observation is that any FFN implements a certain approximation of a corresponding Bayesian network (BN). We characterize various benefits of having this connection. In particular, it results in a new learning algorithm for BNs. We validate the "},"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":"1710.11052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-30T16:31:24Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"93e2b253e34667bd97984268c7b8f8f7cb4b9be15ecd757fa3bebd4a04341787","abstract_canon_sha256":"080e56c7f6455f654c88d5e112b1617b1883c46c75d7433f4f868ed0456e1bc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:45.745557Z","signature_b64":"q6DkEdpO0Nc7pcGS0hHxi2zxYveo1WrhSwwfINs5Yld78y5svzdpQ4PHIoV3Oi3pW++jF2XlI/7qWCXkx8+DCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"079ac24e3378f7ff86e1ae2d6f78aafbd1d4c413013a3f06d66bcce29cf62879","last_reissued_at":"2026-05-18T00:31:45.745023Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:45.745023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Connection between Feed-Forward Neural Networks and Probabilistic Graphical Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Dmitrij Schlesinger","submitted_at":"2017-10-30T16:31:24Z","abstract_excerpt":"Two of the most popular modelling paradigms in computer vision are feed-forward neural networks (FFNs) and probabilistic graphical models (GMs). Various connections between the two have been studied in recent works, such as e.g. expressing mean-field based inference in a GM as an FFN. This paper establishes a new connection between FFNs and GMs. Our key observation is that any FFN implements a certain approximation of a corresponding Bayesian network (BN). We characterize various benefits of having this connection. In particular, it results in a new learning algorithm for BNs. We validate the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.11052","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":"1710.11052","created_at":"2026-05-18T00:31:45.745112+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.11052v1","created_at":"2026-05-18T00:31:45.745112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.11052","created_at":"2026-05-18T00:31:45.745112+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6NMETRTPD37","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6NMETRTPD377BXB","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6NMETRT","created_at":"2026-05-18T12:31:05.417338+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/A6NMETRTPD377BXBVYWW66FK7P","json":"https://pith.science/pith/A6NMETRTPD377BXBVYWW66FK7P.json","graph_json":"https://pith.science/api/pith-number/A6NMETRTPD377BXBVYWW66FK7P/graph.json","events_json":"https://pith.science/api/pith-number/A6NMETRTPD377BXBVYWW66FK7P/events.json","paper":"https://pith.science/paper/A6NMETRT"},"agent_actions":{"view_html":"https://pith.science/pith/A6NMETRTPD377BXBVYWW66FK7P","download_json":"https://pith.science/pith/A6NMETRTPD377BXBVYWW66FK7P.json","view_paper":"https://pith.science/paper/A6NMETRT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.11052&json=true","fetch_graph":"https://pith.science/api/pith-number/A6NMETRTPD377BXBVYWW66FK7P/graph.json","fetch_events":"https://pith.science/api/pith-number/A6NMETRTPD377BXBVYWW66FK7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6NMETRTPD377BXBVYWW66FK7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6NMETRTPD377BXBVYWW66FK7P/action/storage_attestation","attest_author":"https://pith.science/pith/A6NMETRTPD377BXBVYWW66FK7P/action/author_attestation","sign_citation":"https://pith.science/pith/A6NMETRTPD377BXBVYWW66FK7P/action/citation_signature","submit_replication":"https://pith.science/pith/A6NMETRTPD377BXBVYWW66FK7P/action/replication_record"}},"created_at":"2026-05-18T00:31:45.745112+00:00","updated_at":"2026-05-18T00:31:45.745112+00:00"}