{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CX3EEJMIVMHHZJBP7XOOL4MJEP","short_pith_number":"pith:CX3EEJMI","schema_version":"1.0","canonical_sha256":"15f6422588ab0e7ca42ffddce5f18923e367283a4fafec9f837ca888c3d8df1c","source":{"kind":"arxiv","id":"1905.07931","version":1},"attestation_state":"computed","paper":{"title":"Compressed Learning of Deep Neural Networks for OpenCL-Capable Embedded Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jeonghyun Lee, Sangkyun Lee","submitted_at":"2019-05-20T08:02:24Z","abstract_excerpt":"Deep neural networks (DNNs) have been quite successful in solving many complex learning problems. However, DNNs tend to have a large number of learning parameters, leading to a large memory and computation requirement. In this paper, we propose a model compression framework for efficient training and inference of deep neural networks on embedded systems. Our framework provides data structures and kernels for OpenCL-based parallel forward and backward computation in a compressed form. In particular, our method learns sparse representations of parameters using $\\ell_1$-based sparse coding while "},"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":"1905.07931","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-20T08:02:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c71cdd7958d710a53fdf3afe0a10582a42a23c6b41e86741f6b58c7456a16886","abstract_canon_sha256":"74259dd852de73753372e9dde24a6db761349fd332ab1d431f41e020c5269469"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:48.052248Z","signature_b64":"zhKnsF4tD3HV0PLtGzVmd01A7bpoPOlvfchi1Sf147VhG/acB+aNeTG1NxcGL+4nexWEKOdPL6il3t4Gzu4yAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15f6422588ab0e7ca42ffddce5f18923e367283a4fafec9f837ca888c3d8df1c","last_reissued_at":"2026-05-17T23:45:48.051618Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:48.051618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compressed Learning of Deep Neural Networks for OpenCL-Capable Embedded Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jeonghyun Lee, Sangkyun Lee","submitted_at":"2019-05-20T08:02:24Z","abstract_excerpt":"Deep neural networks (DNNs) have been quite successful in solving many complex learning problems. However, DNNs tend to have a large number of learning parameters, leading to a large memory and computation requirement. In this paper, we propose a model compression framework for efficient training and inference of deep neural networks on embedded systems. Our framework provides data structures and kernels for OpenCL-based parallel forward and backward computation in a compressed form. In particular, our method learns sparse representations of parameters using $\\ell_1$-based sparse coding while "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07931","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":"1905.07931","created_at":"2026-05-17T23:45:48.051724+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.07931v1","created_at":"2026-05-17T23:45:48.051724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07931","created_at":"2026-05-17T23:45:48.051724+00:00"},{"alias_kind":"pith_short_12","alias_value":"CX3EEJMIVMHH","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"CX3EEJMIVMHHZJBP","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"CX3EEJMI","created_at":"2026-05-18T12:33:15.570797+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/CX3EEJMIVMHHZJBP7XOOL4MJEP","json":"https://pith.science/pith/CX3EEJMIVMHHZJBP7XOOL4MJEP.json","graph_json":"https://pith.science/api/pith-number/CX3EEJMIVMHHZJBP7XOOL4MJEP/graph.json","events_json":"https://pith.science/api/pith-number/CX3EEJMIVMHHZJBP7XOOL4MJEP/events.json","paper":"https://pith.science/paper/CX3EEJMI"},"agent_actions":{"view_html":"https://pith.science/pith/CX3EEJMIVMHHZJBP7XOOL4MJEP","download_json":"https://pith.science/pith/CX3EEJMIVMHHZJBP7XOOL4MJEP.json","view_paper":"https://pith.science/paper/CX3EEJMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.07931&json=true","fetch_graph":"https://pith.science/api/pith-number/CX3EEJMIVMHHZJBP7XOOL4MJEP/graph.json","fetch_events":"https://pith.science/api/pith-number/CX3EEJMIVMHHZJBP7XOOL4MJEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CX3EEJMIVMHHZJBP7XOOL4MJEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CX3EEJMIVMHHZJBP7XOOL4MJEP/action/storage_attestation","attest_author":"https://pith.science/pith/CX3EEJMIVMHHZJBP7XOOL4MJEP/action/author_attestation","sign_citation":"https://pith.science/pith/CX3EEJMIVMHHZJBP7XOOL4MJEP/action/citation_signature","submit_replication":"https://pith.science/pith/CX3EEJMIVMHHZJBP7XOOL4MJEP/action/replication_record"}},"created_at":"2026-05-17T23:45:48.051724+00:00","updated_at":"2026-05-17T23:45:48.051724+00:00"}