{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DGSPN27VKYYRBLXSGXBELQ22OW","short_pith_number":"pith:DGSPN27V","schema_version":"1.0","canonical_sha256":"19a4f6ebf5563110aef235c245c35a75ab7bcbaa1b501718069aeb83c31ecad9","source":{"kind":"arxiv","id":"1807.07362","version":1},"attestation_state":"computed","paper":{"title":"Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Nicol\\'as Navarro-Guerrero, Stefan Wermter, Sven Magg, Tobias Hinz","submitted_at":"2018-07-19T12:25:29Z","abstract_excerpt":"Most learning algorithms require the practitioner to manually set the values of many hyperparameters before the learning process can begin. However, with modern algorithms, the evaluation of a given hyperparameter setting can take a considerable amount of time and the search space is often very high-dimensional. We suggest using a lower-dimensional representation of the original data to quickly identify promising areas in the hyperparameter space. This information can then be used to initialize the optimization algorithm for the original, higher-dimensional data. We compare this approach with "},"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":"1807.07362","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-07-19T12:25:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6a0bdb9da4ab80c85f2b9dd335b7f28a66e8a7398bf3a7d245613058b207e964","abstract_canon_sha256":"1eefe191f5aba274c403e4758760e76d4935c7137bf67dafbd543ec075592e06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:20.350211Z","signature_b64":"vhxjFS9MMPyofKExJztrrOiyOkdNq4jbJLU3X8xh70eWQXaZ04P8twaZ12Aal+jkOWFMQbH8C8wBbiHQKZNfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19a4f6ebf5563110aef235c245c35a75ab7bcbaa1b501718069aeb83c31ecad9","last_reissued_at":"2026-05-18T00:10:20.349716Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:20.349716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Nicol\\'as Navarro-Guerrero, Stefan Wermter, Sven Magg, Tobias Hinz","submitted_at":"2018-07-19T12:25:29Z","abstract_excerpt":"Most learning algorithms require the practitioner to manually set the values of many hyperparameters before the learning process can begin. However, with modern algorithms, the evaluation of a given hyperparameter setting can take a considerable amount of time and the search space is often very high-dimensional. We suggest using a lower-dimensional representation of the original data to quickly identify promising areas in the hyperparameter space. This information can then be used to initialize the optimization algorithm for the original, higher-dimensional data. We compare this approach with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.07362","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":"1807.07362","created_at":"2026-05-18T00:10:20.349775+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.07362v1","created_at":"2026-05-18T00:10:20.349775+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.07362","created_at":"2026-05-18T00:10:20.349775+00:00"},{"alias_kind":"pith_short_12","alias_value":"DGSPN27VKYYR","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DGSPN27VKYYRBLXS","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DGSPN27V","created_at":"2026-05-18T12:32:19.392346+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/DGSPN27VKYYRBLXSGXBELQ22OW","json":"https://pith.science/pith/DGSPN27VKYYRBLXSGXBELQ22OW.json","graph_json":"https://pith.science/api/pith-number/DGSPN27VKYYRBLXSGXBELQ22OW/graph.json","events_json":"https://pith.science/api/pith-number/DGSPN27VKYYRBLXSGXBELQ22OW/events.json","paper":"https://pith.science/paper/DGSPN27V"},"agent_actions":{"view_html":"https://pith.science/pith/DGSPN27VKYYRBLXSGXBELQ22OW","download_json":"https://pith.science/pith/DGSPN27VKYYRBLXSGXBELQ22OW.json","view_paper":"https://pith.science/paper/DGSPN27V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.07362&json=true","fetch_graph":"https://pith.science/api/pith-number/DGSPN27VKYYRBLXSGXBELQ22OW/graph.json","fetch_events":"https://pith.science/api/pith-number/DGSPN27VKYYRBLXSGXBELQ22OW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DGSPN27VKYYRBLXSGXBELQ22OW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DGSPN27VKYYRBLXSGXBELQ22OW/action/storage_attestation","attest_author":"https://pith.science/pith/DGSPN27VKYYRBLXSGXBELQ22OW/action/author_attestation","sign_citation":"https://pith.science/pith/DGSPN27VKYYRBLXSGXBELQ22OW/action/citation_signature","submit_replication":"https://pith.science/pith/DGSPN27VKYYRBLXSGXBELQ22OW/action/replication_record"}},"created_at":"2026-05-18T00:10:20.349775+00:00","updated_at":"2026-05-18T00:10:20.349775+00:00"}