{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:M574CCIY7DVHWFTUIYBCFLZSKW","short_pith_number":"pith:M574CCIY","schema_version":"1.0","canonical_sha256":"677fc10918f8ea7b1674460222af3255b7eb211ec10768fd4bafae601534779c","source":{"kind":"arxiv","id":"1607.05423","version":1},"attestation_state":"computed","paper":{"title":"Training Skinny Deep Neural Networks with Iterative Hard Thresholding Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiashi Feng, Shuicheng Yan, Xiaojie Jin, Xiaotong Yuan","submitted_at":"2016-07-19T06:41:31Z","abstract_excerpt":"Deep neural networks have achieved remarkable success in a wide range of practical problems. However, due to the inherent large parameter space, deep models are notoriously prone to overfitting and difficult to be deployed in portable devices with limited memory. In this paper, we propose an iterative hard thresholding (IHT) approach to train Skinny Deep Neural Networks (SDNNs). An SDNN has much fewer parameters yet can achieve competitive or even better performance than its full CNN counterpart. More concretely, the IHT approach trains an SDNN through following two alternative phases: (I) per"},"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":"1607.05423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-07-19T06:41:31Z","cross_cats_sorted":[],"title_canon_sha256":"3dd4b088942dab2a24d55cd52cd3535f884e4a397e751aa06b5e311b4424bd23","abstract_canon_sha256":"44277ac5650a08b471d2d2eb78da09cfb062e3cf3dec5a58e6bcea32372601a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:46.903050Z","signature_b64":"gbiojewpGDPW962zTtnXwUzOZILDswLA7kyEH/suIMuPmLWglRQZAtI4tNPk+VhAugvTWRUC4aup3Po5SqUvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"677fc10918f8ea7b1674460222af3255b7eb211ec10768fd4bafae601534779c","last_reissued_at":"2026-05-18T01:10:46.902541Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:46.902541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Skinny Deep Neural Networks with Iterative Hard Thresholding Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiashi Feng, Shuicheng Yan, Xiaojie Jin, Xiaotong Yuan","submitted_at":"2016-07-19T06:41:31Z","abstract_excerpt":"Deep neural networks have achieved remarkable success in a wide range of practical problems. However, due to the inherent large parameter space, deep models are notoriously prone to overfitting and difficult to be deployed in portable devices with limited memory. In this paper, we propose an iterative hard thresholding (IHT) approach to train Skinny Deep Neural Networks (SDNNs). An SDNN has much fewer parameters yet can achieve competitive or even better performance than its full CNN counterpart. More concretely, the IHT approach trains an SDNN through following two alternative phases: (I) per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.05423","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":"1607.05423","created_at":"2026-05-18T01:10:46.902626+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.05423v1","created_at":"2026-05-18T01:10:46.902626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.05423","created_at":"2026-05-18T01:10:46.902626+00:00"},{"alias_kind":"pith_short_12","alias_value":"M574CCIY7DVH","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"M574CCIY7DVHWFTU","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"M574CCIY","created_at":"2026-05-18T12:30:29.479603+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/M574CCIY7DVHWFTUIYBCFLZSKW","json":"https://pith.science/pith/M574CCIY7DVHWFTUIYBCFLZSKW.json","graph_json":"https://pith.science/api/pith-number/M574CCIY7DVHWFTUIYBCFLZSKW/graph.json","events_json":"https://pith.science/api/pith-number/M574CCIY7DVHWFTUIYBCFLZSKW/events.json","paper":"https://pith.science/paper/M574CCIY"},"agent_actions":{"view_html":"https://pith.science/pith/M574CCIY7DVHWFTUIYBCFLZSKW","download_json":"https://pith.science/pith/M574CCIY7DVHWFTUIYBCFLZSKW.json","view_paper":"https://pith.science/paper/M574CCIY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.05423&json=true","fetch_graph":"https://pith.science/api/pith-number/M574CCIY7DVHWFTUIYBCFLZSKW/graph.json","fetch_events":"https://pith.science/api/pith-number/M574CCIY7DVHWFTUIYBCFLZSKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M574CCIY7DVHWFTUIYBCFLZSKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M574CCIY7DVHWFTUIYBCFLZSKW/action/storage_attestation","attest_author":"https://pith.science/pith/M574CCIY7DVHWFTUIYBCFLZSKW/action/author_attestation","sign_citation":"https://pith.science/pith/M574CCIY7DVHWFTUIYBCFLZSKW/action/citation_signature","submit_replication":"https://pith.science/pith/M574CCIY7DVHWFTUIYBCFLZSKW/action/replication_record"}},"created_at":"2026-05-18T01:10:46.902626+00:00","updated_at":"2026-05-18T01:10:46.902626+00:00"}