{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MYGDESCNYGGF3D72LRPKXO4GIA","short_pith_number":"pith:MYGDESCN","schema_version":"1.0","canonical_sha256":"660c32484dc18c5d8ffa5c5eabbb8640302e393858490e0e4c12ff8f57304b29","source":{"kind":"arxiv","id":"1811.02657","version":2},"attestation_state":"computed","paper":{"title":"A Bayesian Perspective of Convolutional Neural Networks through a Deconvolutional Generative Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.CV","authors_text":"Anima Anandkumar, Ankit Patel, Michael I. Jordan, Nhat Ho, Richard G. Baraniuk, Tan Nguyen","submitted_at":"2018-11-01T01:27:37Z","abstract_excerpt":"Inspired by the success of Convolutional Neural Networks (CNNs) for supervised prediction in images, we design the Deconvolutional Generative Model (DGM), a new probabilistic generative model whose inference calculations correspond to those in a given CNN architecture. The DGM uses a CNN to design the prior distribution in the probabilistic model. Furthermore, the DGM generates images from coarse to finer scales. It introduces a small set of latent variables at each scale, and enforces dependencies among all the latent variables via a conjugate prior distribution. This conjugate prior yields a"},"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":"1811.02657","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-01T01:27:37Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"bfefcf80518833e66c44a6595199e45410e2896651d11b518578210bde77decb","abstract_canon_sha256":"5853b8b789f6949123e5a3e9b3a562d7c76e6bf0ca091b9499708986107ffa32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:36.029800Z","signature_b64":"UuVJB2W7gPoUzIqKy9u7necUDKm15grG52pdzpvNFKatvTVCNkfHsiHuGZLASJnqG+ryVChFIP736DQBv+eSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"660c32484dc18c5d8ffa5c5eabbb8640302e393858490e0e4c12ff8f57304b29","last_reissued_at":"2026-07-05T00:24:36.029312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:36.029312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Bayesian Perspective of Convolutional Neural Networks through a Deconvolutional Generative Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.CV","authors_text":"Anima Anandkumar, Ankit Patel, Michael I. Jordan, Nhat Ho, Richard G. Baraniuk, Tan Nguyen","submitted_at":"2018-11-01T01:27:37Z","abstract_excerpt":"Inspired by the success of Convolutional Neural Networks (CNNs) for supervised prediction in images, we design the Deconvolutional Generative Model (DGM), a new probabilistic generative model whose inference calculations correspond to those in a given CNN architecture. The DGM uses a CNN to design the prior distribution in the probabilistic model. Furthermore, the DGM generates images from coarse to finer scales. It introduces a small set of latent variables at each scale, and enforces dependencies among all the latent variables via a conjugate prior distribution. This conjugate prior yields a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02657","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/1811.02657/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":"1811.02657","created_at":"2026-07-05T00:24:36.029377+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.02657v2","created_at":"2026-07-05T00:24:36.029377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02657","created_at":"2026-07-05T00:24:36.029377+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYGDESCNYGGF","created_at":"2026-07-05T00:24:36.029377+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYGDESCNYGGF3D72","created_at":"2026-07-05T00:24:36.029377+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYGDESCN","created_at":"2026-07-05T00:24:36.029377+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.04572","citing_title":"Out-of-Distribution Detection Using Neural Rendering Generative Models","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYGDESCNYGGF3D72LRPKXO4GIA","json":"https://pith.science/pith/MYGDESCNYGGF3D72LRPKXO4GIA.json","graph_json":"https://pith.science/api/pith-number/MYGDESCNYGGF3D72LRPKXO4GIA/graph.json","events_json":"https://pith.science/api/pith-number/MYGDESCNYGGF3D72LRPKXO4GIA/events.json","paper":"https://pith.science/paper/MYGDESCN"},"agent_actions":{"view_html":"https://pith.science/pith/MYGDESCNYGGF3D72LRPKXO4GIA","download_json":"https://pith.science/pith/MYGDESCNYGGF3D72LRPKXO4GIA.json","view_paper":"https://pith.science/paper/MYGDESCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.02657&json=true","fetch_graph":"https://pith.science/api/pith-number/MYGDESCNYGGF3D72LRPKXO4GIA/graph.json","fetch_events":"https://pith.science/api/pith-number/MYGDESCNYGGF3D72LRPKXO4GIA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYGDESCNYGGF3D72LRPKXO4GIA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYGDESCNYGGF3D72LRPKXO4GIA/action/storage_attestation","attest_author":"https://pith.science/pith/MYGDESCNYGGF3D72LRPKXO4GIA/action/author_attestation","sign_citation":"https://pith.science/pith/MYGDESCNYGGF3D72LRPKXO4GIA/action/citation_signature","submit_replication":"https://pith.science/pith/MYGDESCNYGGF3D72LRPKXO4GIA/action/replication_record"}},"created_at":"2026-07-05T00:24:36.029377+00:00","updated_at":"2026-07-05T00:24:36.029377+00:00"}