{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:JUWVSUHRTJCBLKZJOTATHUP3OT","short_pith_number":"pith:JUWVSUHR","schema_version":"1.0","canonical_sha256":"4d2d5950f19a4415ab2974c133d1fb74de6256aebe954986b4d2489aadafdbd7","source":{"kind":"arxiv","id":"1112.6209","version":5},"attestation_state":"computed","paper":{"title":"Building high-level features using large scale unsupervised learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Y. Ng, Greg S. Corrado, Jeff Dean, Kai Chen, Marc'Aurelio Ranzato, Matthieu Devin, Quoc V. Le, Rajat Monga","submitted_at":"2011-12-29T00:26:54Z","abstract_excerpt":"We consider the problem of building high-level, class-specific feature detectors from only unlabeled data. For example, is it possible to learn a face detector using only unlabeled images? To answer this, we train a 9-layered locally connected sparse autoencoder with pooling and local contrast normalization on a large dataset of images (the model has 1 billion connections, the dataset has 10 million 200x200 pixel images downloaded from the Internet). We train this network using model parallelism and asynchronous SGD on a cluster with 1,000 machines (16,000 cores) for three days. Contrary to wh"},"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":"1112.6209","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-12-29T00:26:54Z","cross_cats_sorted":[],"title_canon_sha256":"9af34454b3a87c69a2dab2b9c148d082f9ba87224692914624217d55e8ae5437","abstract_canon_sha256":"07d01d4d1320d21bd36793a607b9ebade9851dbd953b721d0441996cefb4ad6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:22.790168Z","signature_b64":"OhJ6P3enqpiMhMelqKCBLKdHgh6SPiy/06qXcJ1LSeSN7SrNq69A8QHItLQGK2dYfPIkGZ8K48ZU08a/RiL0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d2d5950f19a4415ab2974c133d1fb74de6256aebe954986b4d2489aadafdbd7","last_reissued_at":"2026-05-18T00:46:22.789742Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:22.789742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Building high-level features using large scale unsupervised learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Y. Ng, Greg S. Corrado, Jeff Dean, Kai Chen, Marc'Aurelio Ranzato, Matthieu Devin, Quoc V. Le, Rajat Monga","submitted_at":"2011-12-29T00:26:54Z","abstract_excerpt":"We consider the problem of building high-level, class-specific feature detectors from only unlabeled data. For example, is it possible to learn a face detector using only unlabeled images? To answer this, we train a 9-layered locally connected sparse autoencoder with pooling and local contrast normalization on a large dataset of images (the model has 1 billion connections, the dataset has 10 million 200x200 pixel images downloaded from the Internet). We train this network using model parallelism and asynchronous SGD on a cluster with 1,000 machines (16,000 cores) for three days. Contrary to wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1112.6209","kind":"arxiv","version":5},"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":"1112.6209","created_at":"2026-05-18T00:46:22.789799+00:00"},{"alias_kind":"arxiv_version","alias_value":"1112.6209v5","created_at":"2026-05-18T00:46:22.789799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1112.6209","created_at":"2026-05-18T00:46:22.789799+00:00"},{"alias_kind":"pith_short_12","alias_value":"JUWVSUHRTJCB","created_at":"2026-05-18T12:26:32.869790+00:00"},{"alias_kind":"pith_short_16","alias_value":"JUWVSUHRTJCBLKZJ","created_at":"2026-05-18T12:26:32.869790+00:00"},{"alias_kind":"pith_short_8","alias_value":"JUWVSUHR","created_at":"2026-05-18T12:26:32.869790+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1312.6199","citing_title":"Intriguing properties of neural networks","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JUWVSUHRTJCBLKZJOTATHUP3OT","json":"https://pith.science/pith/JUWVSUHRTJCBLKZJOTATHUP3OT.json","graph_json":"https://pith.science/api/pith-number/JUWVSUHRTJCBLKZJOTATHUP3OT/graph.json","events_json":"https://pith.science/api/pith-number/JUWVSUHRTJCBLKZJOTATHUP3OT/events.json","paper":"https://pith.science/paper/JUWVSUHR"},"agent_actions":{"view_html":"https://pith.science/pith/JUWVSUHRTJCBLKZJOTATHUP3OT","download_json":"https://pith.science/pith/JUWVSUHRTJCBLKZJOTATHUP3OT.json","view_paper":"https://pith.science/paper/JUWVSUHR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1112.6209&json=true","fetch_graph":"https://pith.science/api/pith-number/JUWVSUHRTJCBLKZJOTATHUP3OT/graph.json","fetch_events":"https://pith.science/api/pith-number/JUWVSUHRTJCBLKZJOTATHUP3OT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JUWVSUHRTJCBLKZJOTATHUP3OT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JUWVSUHRTJCBLKZJOTATHUP3OT/action/storage_attestation","attest_author":"https://pith.science/pith/JUWVSUHRTJCBLKZJOTATHUP3OT/action/author_attestation","sign_citation":"https://pith.science/pith/JUWVSUHRTJCBLKZJOTATHUP3OT/action/citation_signature","submit_replication":"https://pith.science/pith/JUWVSUHRTJCBLKZJOTATHUP3OT/action/replication_record"}},"created_at":"2026-05-18T00:46:22.789799+00:00","updated_at":"2026-05-18T00:46:22.789799+00:00"}