{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:354PJKBFNLZKDEYAUR3WP7UFKF","short_pith_number":"pith:354PJKBF","schema_version":"1.0","canonical_sha256":"df78f4a8256af2a19300a47767fe85514c4b9f2d90cf0c596f029369fbe2dae3","source":{"kind":"arxiv","id":"1805.07821","version":3},"attestation_state":"computed","paper":{"title":"Low-Cost Parameterizations of Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.NA"],"primary_cat":"cs.NA","authors_text":"Eldad Haber, Eran Treister, Lars Ruthotto, Michal Sharoni, Sapir Zafrani","submitted_at":"2018-05-20T20:17:47Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) filter the input data using a series of spatial convolution operators with compactly supported stencils and point-wise nonlinearities. Commonly, the convolution operators couple features from all channels. For wide networks, this leads to immense computational cost in the training of and prediction with CNNs. In this paper, we present novel ways to parameterize the convolution more efficiently, aiming to decrease the number of parameters in CNNs and their computational complexity. We propose new architectures that use a sparser coupling between the channels"},"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":"1805.07821","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NA","submitted_at":"2018-05-20T20:17:47Z","cross_cats_sorted":["math.NA"],"title_canon_sha256":"beca99e63fdfed8523e0628b7e297c3ea5ffcaae7202c253ebe104beac5c5c4c","abstract_canon_sha256":"14c20254cbd896c15ab0f7839f7824c982b9bff3dee13bc9cb98b23f4c8d4e01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:12.934642Z","signature_b64":"oQ9/4Ydvu5UvgZsvUVvZJWoCQeEF282OPeiufi6CiNOx2Go2lZyyLwEJcmId1cF9eaAVEMQKgLyqoEbibaW5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df78f4a8256af2a19300a47767fe85514c4b9f2d90cf0c596f029369fbe2dae3","last_reissued_at":"2026-05-18T00:04:12.933925Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:12.933925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Cost Parameterizations of Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.NA"],"primary_cat":"cs.NA","authors_text":"Eldad Haber, Eran Treister, Lars Ruthotto, Michal Sharoni, Sapir Zafrani","submitted_at":"2018-05-20T20:17:47Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) filter the input data using a series of spatial convolution operators with compactly supported stencils and point-wise nonlinearities. Commonly, the convolution operators couple features from all channels. For wide networks, this leads to immense computational cost in the training of and prediction with CNNs. In this paper, we present novel ways to parameterize the convolution more efficiently, aiming to decrease the number of parameters in CNNs and their computational complexity. We propose new architectures that use a sparser coupling between the channels"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07821","kind":"arxiv","version":3},"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":"1805.07821","created_at":"2026-05-18T00:04:12.934031+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.07821v3","created_at":"2026-05-18T00:04:12.934031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07821","created_at":"2026-05-18T00:04:12.934031+00:00"},{"alias_kind":"pith_short_12","alias_value":"354PJKBFNLZK","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"354PJKBFNLZKDEYA","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"354PJKBF","created_at":"2026-05-18T12:32:02.567920+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/354PJKBFNLZKDEYAUR3WP7UFKF","json":"https://pith.science/pith/354PJKBFNLZKDEYAUR3WP7UFKF.json","graph_json":"https://pith.science/api/pith-number/354PJKBFNLZKDEYAUR3WP7UFKF/graph.json","events_json":"https://pith.science/api/pith-number/354PJKBFNLZKDEYAUR3WP7UFKF/events.json","paper":"https://pith.science/paper/354PJKBF"},"agent_actions":{"view_html":"https://pith.science/pith/354PJKBFNLZKDEYAUR3WP7UFKF","download_json":"https://pith.science/pith/354PJKBFNLZKDEYAUR3WP7UFKF.json","view_paper":"https://pith.science/paper/354PJKBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.07821&json=true","fetch_graph":"https://pith.science/api/pith-number/354PJKBFNLZKDEYAUR3WP7UFKF/graph.json","fetch_events":"https://pith.science/api/pith-number/354PJKBFNLZKDEYAUR3WP7UFKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/354PJKBFNLZKDEYAUR3WP7UFKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/354PJKBFNLZKDEYAUR3WP7UFKF/action/storage_attestation","attest_author":"https://pith.science/pith/354PJKBFNLZKDEYAUR3WP7UFKF/action/author_attestation","sign_citation":"https://pith.science/pith/354PJKBFNLZKDEYAUR3WP7UFKF/action/citation_signature","submit_replication":"https://pith.science/pith/354PJKBFNLZKDEYAUR3WP7UFKF/action/replication_record"}},"created_at":"2026-05-18T00:04:12.934031+00:00","updated_at":"2026-05-18T00:04:12.934031+00:00"}