{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:2BBSZDWS3HR4XA3OITAHLFKVC6","short_pith_number":"pith:2BBSZDWS","schema_version":"1.0","canonical_sha256":"d0432c8ed2d9e3cb836e44c0759555179a4a240f9017d72df16bd78aa93cf87d","source":{"kind":"arxiv","id":"1601.06815","version":1},"attestation_state":"computed","paper":{"title":"Very Efficient Training of Convolutional Neural Networks using Fast Fourier Transform and Overlap-and-Add","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Andres Rodriguez, Tyler Highlander","submitted_at":"2016-01-25T21:29:11Z","abstract_excerpt":"Convolutional neural networks (CNNs) are currently state-of-the-art for various classification tasks, but are computationally expensive. Propagating through the convolutional layers is very slow, as each kernel in each layer must sequentially calculate many dot products for a single forward and backward propagation which equates to $\\mathcal{O}(N^{2}n^{2})$ per kernel per layer where the inputs are $N \\times N$ arrays and the kernels are $n \\times n$ arrays. Convolution can be efficiently performed as a Hadamard product in the frequency domain. The bottleneck is the transformation which has 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":"1601.06815","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2016-01-25T21:29:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9f6a587f9db608d3e3c091b6cc36f26b444cd6c36de4178a0d28e567d4ac5e08","abstract_canon_sha256":"30c6fb05ce8316db2ae00fca8e2ac65414b9b546882d809bceed1ceef95b4afd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:21:59.744307Z","signature_b64":"ja9pbpZJ6IgC0SM2+QiHqWgA+pqq3gbB1GX+ZuVfkLW8kWbjcze69S4I3V+hyj8dDp7TzHAInnpLyUxvi3kRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0432c8ed2d9e3cb836e44c0759555179a4a240f9017d72df16bd78aa93cf87d","last_reissued_at":"2026-05-18T01:21:59.743765Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:21:59.743765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Very Efficient Training of Convolutional Neural Networks using Fast Fourier Transform and Overlap-and-Add","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Andres Rodriguez, Tyler Highlander","submitted_at":"2016-01-25T21:29:11Z","abstract_excerpt":"Convolutional neural networks (CNNs) are currently state-of-the-art for various classification tasks, but are computationally expensive. Propagating through the convolutional layers is very slow, as each kernel in each layer must sequentially calculate many dot products for a single forward and backward propagation which equates to $\\mathcal{O}(N^{2}n^{2})$ per kernel per layer where the inputs are $N \\times N$ arrays and the kernels are $n \\times n$ arrays. Convolution can be efficiently performed as a Hadamard product in the frequency domain. The bottleneck is the transformation which has a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.06815","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":"1601.06815","created_at":"2026-05-18T01:21:59.743867+00:00"},{"alias_kind":"arxiv_version","alias_value":"1601.06815v1","created_at":"2026-05-18T01:21:59.743867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.06815","created_at":"2026-05-18T01:21:59.743867+00:00"},{"alias_kind":"pith_short_12","alias_value":"2BBSZDWS3HR4","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_16","alias_value":"2BBSZDWS3HR4XA3O","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_8","alias_value":"2BBSZDWS","created_at":"2026-05-18T12:29:52.810259+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.04969","citing_title":"General Transform: A Unified Framework for Adaptive Transform to Enhance Representations","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2BBSZDWS3HR4XA3OITAHLFKVC6","json":"https://pith.science/pith/2BBSZDWS3HR4XA3OITAHLFKVC6.json","graph_json":"https://pith.science/api/pith-number/2BBSZDWS3HR4XA3OITAHLFKVC6/graph.json","events_json":"https://pith.science/api/pith-number/2BBSZDWS3HR4XA3OITAHLFKVC6/events.json","paper":"https://pith.science/paper/2BBSZDWS"},"agent_actions":{"view_html":"https://pith.science/pith/2BBSZDWS3HR4XA3OITAHLFKVC6","download_json":"https://pith.science/pith/2BBSZDWS3HR4XA3OITAHLFKVC6.json","view_paper":"https://pith.science/paper/2BBSZDWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1601.06815&json=true","fetch_graph":"https://pith.science/api/pith-number/2BBSZDWS3HR4XA3OITAHLFKVC6/graph.json","fetch_events":"https://pith.science/api/pith-number/2BBSZDWS3HR4XA3OITAHLFKVC6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2BBSZDWS3HR4XA3OITAHLFKVC6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2BBSZDWS3HR4XA3OITAHLFKVC6/action/storage_attestation","attest_author":"https://pith.science/pith/2BBSZDWS3HR4XA3OITAHLFKVC6/action/author_attestation","sign_citation":"https://pith.science/pith/2BBSZDWS3HR4XA3OITAHLFKVC6/action/citation_signature","submit_replication":"https://pith.science/pith/2BBSZDWS3HR4XA3OITAHLFKVC6/action/replication_record"}},"created_at":"2026-05-18T01:21:59.743867+00:00","updated_at":"2026-05-18T01:21:59.743867+00:00"}