{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:R4MOHWNMHZYBIGJUDCNRUSLBCI","short_pith_number":"pith:R4MOHWNM","schema_version":"1.0","canonical_sha256":"8f18e3d9ac3e70141934189b1a496112078d1961b8e1454d4903352eb2bf5dd3","source":{"kind":"arxiv","id":"1504.01483","version":1},"attestation_state":"computed","paper":{"title":"Transferring Knowledge from a RNN to a DNN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ian Lane, Nan Rosemary Ke, William Chan","submitted_at":"2015-04-07T06:15:44Z","abstract_excerpt":"Deep Neural Network (DNN) acoustic models have yielded many state-of-the-art results in Automatic Speech Recognition (ASR) tasks. More recently, Recurrent Neural Network (RNN) models have been shown to outperform DNNs counterparts. However, state-of-the-art DNN and RNN models tend to be impractical to deploy on embedded systems with limited computational capacity. Traditionally, the approach for embedded platforms is to either train a small DNN directly, or to train a small DNN that learns the output distribution of a large DNN. In this paper, we utilize a state-of-the-art RNN to transfer know"},"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":"1504.01483","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-04-07T06:15:44Z","cross_cats_sorted":["cs.CL","cs.NE","stat.ML"],"title_canon_sha256":"461c5748dbcb6acff2f2741c4d28646d340fdb0b54485fda4021ac91de588fa3","abstract_canon_sha256":"617a49e1b7144320e510fc514b7f3e9fa6688825d0cbbe519f3bb99d2604eb68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:19:27.005446Z","signature_b64":"6HfBEMKrCHj1hZj8L2PMB6QjyV/3pT3c3bjNtHwGmsiJyRtRKt2zBUY7wQfJSpdpMiYF5XqRnYXinpPawlKxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f18e3d9ac3e70141934189b1a496112078d1961b8e1454d4903352eb2bf5dd3","last_reissued_at":"2026-05-18T02:19:27.004817Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:19:27.004817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transferring Knowledge from a RNN to a DNN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ian Lane, Nan Rosemary Ke, William Chan","submitted_at":"2015-04-07T06:15:44Z","abstract_excerpt":"Deep Neural Network (DNN) acoustic models have yielded many state-of-the-art results in Automatic Speech Recognition (ASR) tasks. More recently, Recurrent Neural Network (RNN) models have been shown to outperform DNNs counterparts. However, state-of-the-art DNN and RNN models tend to be impractical to deploy on embedded systems with limited computational capacity. Traditionally, the approach for embedded platforms is to either train a small DNN directly, or to train a small DNN that learns the output distribution of a large DNN. In this paper, we utilize a state-of-the-art RNN to transfer know"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.01483","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":"1504.01483","created_at":"2026-05-18T02:19:27.004916+00:00"},{"alias_kind":"arxiv_version","alias_value":"1504.01483v1","created_at":"2026-05-18T02:19:27.004916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.01483","created_at":"2026-05-18T02:19:27.004916+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4MOHWNMHZYB","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4MOHWNMHZYBIGJU","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4MOHWNM","created_at":"2026-05-18T12:29:39.896362+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/R4MOHWNMHZYBIGJUDCNRUSLBCI","json":"https://pith.science/pith/R4MOHWNMHZYBIGJUDCNRUSLBCI.json","graph_json":"https://pith.science/api/pith-number/R4MOHWNMHZYBIGJUDCNRUSLBCI/graph.json","events_json":"https://pith.science/api/pith-number/R4MOHWNMHZYBIGJUDCNRUSLBCI/events.json","paper":"https://pith.science/paper/R4MOHWNM"},"agent_actions":{"view_html":"https://pith.science/pith/R4MOHWNMHZYBIGJUDCNRUSLBCI","download_json":"https://pith.science/pith/R4MOHWNMHZYBIGJUDCNRUSLBCI.json","view_paper":"https://pith.science/paper/R4MOHWNM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1504.01483&json=true","fetch_graph":"https://pith.science/api/pith-number/R4MOHWNMHZYBIGJUDCNRUSLBCI/graph.json","fetch_events":"https://pith.science/api/pith-number/R4MOHWNMHZYBIGJUDCNRUSLBCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4MOHWNMHZYBIGJUDCNRUSLBCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4MOHWNMHZYBIGJUDCNRUSLBCI/action/storage_attestation","attest_author":"https://pith.science/pith/R4MOHWNMHZYBIGJUDCNRUSLBCI/action/author_attestation","sign_citation":"https://pith.science/pith/R4MOHWNMHZYBIGJUDCNRUSLBCI/action/citation_signature","submit_replication":"https://pith.science/pith/R4MOHWNMHZYBIGJUDCNRUSLBCI/action/replication_record"}},"created_at":"2026-05-18T02:19:27.004916+00:00","updated_at":"2026-05-18T02:19:27.004916+00:00"}