{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GV2PYSYIHOTX33B7XAQWPT4MDR","short_pith_number":"pith:GV2PYSYI","schema_version":"1.0","canonical_sha256":"3574fc4b083ba77dec3fb82167cf8c1c7fa9a5368a3b0ff9217d79da56e2b42e","source":{"kind":"arxiv","id":"1704.08362","version":1},"attestation_state":"computed","paper":{"title":"A New Type of Neurons for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Fenglei Fan, Ge Wang, Wenxiang Cong","submitted_at":"2017-04-26T22:02:25Z","abstract_excerpt":"In machine learning, the use of an artificial neural network is the mainstream approach. Such a network consists of layers of neurons. These neurons are of the same type characterized by the two features: (1) an inner product of an input vector and a matching weighting vector of trainable parameters and (2) a nonlinear excitation function. Here we investigate the possibility of replacing the inner product with a quadratic function of the input vector, thereby upgrading the 1st order neuron to the 2nd order neuron, empowering individual neurons, and facilitating the optimization of neural netwo"},"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":"1704.08362","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-04-26T22:02:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"82287782b2e4760e4e621f050ca30be7cc4509d128a02580b736d64e2f41bd2c","abstract_canon_sha256":"1164b740b2efb845d3d574cd6db5611abca5aeb92e0a428c79d98f83457afce7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:27.862441Z","signature_b64":"65Qa8yYdzuyPHQh3PdEIN5+nv5vdSu/29ZL6uB/4/M8FJew3Oye4KOFEF6sgTfCm3xwrnm5/UOqLgmWtKJu4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3574fc4b083ba77dec3fb82167cf8c1c7fa9a5368a3b0ff9217d79da56e2b42e","last_reissued_at":"2026-05-18T00:45:27.862050Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:27.862050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A New Type of Neurons for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Fenglei Fan, Ge Wang, Wenxiang Cong","submitted_at":"2017-04-26T22:02:25Z","abstract_excerpt":"In machine learning, the use of an artificial neural network is the mainstream approach. Such a network consists of layers of neurons. These neurons are of the same type characterized by the two features: (1) an inner product of an input vector and a matching weighting vector of trainable parameters and (2) a nonlinear excitation function. Here we investigate the possibility of replacing the inner product with a quadratic function of the input vector, thereby upgrading the 1st order neuron to the 2nd order neuron, empowering individual neurons, and facilitating the optimization of neural netwo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.08362","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":"1704.08362","created_at":"2026-05-18T00:45:27.862108+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.08362v1","created_at":"2026-05-18T00:45:27.862108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.08362","created_at":"2026-05-18T00:45:27.862108+00:00"},{"alias_kind":"pith_short_12","alias_value":"GV2PYSYIHOTX","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"GV2PYSYIHOTX33B7","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"GV2PYSYI","created_at":"2026-05-18T12:31:18.294218+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/GV2PYSYIHOTX33B7XAQWPT4MDR","json":"https://pith.science/pith/GV2PYSYIHOTX33B7XAQWPT4MDR.json","graph_json":"https://pith.science/api/pith-number/GV2PYSYIHOTX33B7XAQWPT4MDR/graph.json","events_json":"https://pith.science/api/pith-number/GV2PYSYIHOTX33B7XAQWPT4MDR/events.json","paper":"https://pith.science/paper/GV2PYSYI"},"agent_actions":{"view_html":"https://pith.science/pith/GV2PYSYIHOTX33B7XAQWPT4MDR","download_json":"https://pith.science/pith/GV2PYSYIHOTX33B7XAQWPT4MDR.json","view_paper":"https://pith.science/paper/GV2PYSYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.08362&json=true","fetch_graph":"https://pith.science/api/pith-number/GV2PYSYIHOTX33B7XAQWPT4MDR/graph.json","fetch_events":"https://pith.science/api/pith-number/GV2PYSYIHOTX33B7XAQWPT4MDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GV2PYSYIHOTX33B7XAQWPT4MDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GV2PYSYIHOTX33B7XAQWPT4MDR/action/storage_attestation","attest_author":"https://pith.science/pith/GV2PYSYIHOTX33B7XAQWPT4MDR/action/author_attestation","sign_citation":"https://pith.science/pith/GV2PYSYIHOTX33B7XAQWPT4MDR/action/citation_signature","submit_replication":"https://pith.science/pith/GV2PYSYIHOTX33B7XAQWPT4MDR/action/replication_record"}},"created_at":"2026-05-18T00:45:27.862108+00:00","updated_at":"2026-05-18T00:45:27.862108+00:00"}