{"id":"W3114868419","doi":"10.1016/j.asoc.2020.107051","title":"A tucker decomposition based knowledge distillation for intelligent edge applications","year":2020,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"National Key Research and Development Program of China; Basic Research Programs of Sichuan Province; Department of Science and Technology of Sichuan Province; National Natural Science Foundation of China","keywords":"Distillation; Computer science; Enhanced Data Rates for GSM Evolution; Decomposition; Ideal (ethics); Variance (accounting); Artificial intelligence; Tucker decomposition; Machine learning; Mathematics; Chemistry; Chromatography; Tensor decomposition","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004553166,0.0006904379,0.001062918,0.00077019,0.0006932281,0.001195726,0.001459755,0.001151623,0.008502202],"category_scores_gemma":[0.001367705,0.0004121975,0.0008392268,0.001008517,0.0005274422,0.001740282,0.001929792,0.001890885,0.001730183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004500309,"about_ca_system_score_gemma":0.001457715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004402445,"about_ca_topic_score_gemma":0.007095374,"domain_scores_codex":[0.999663,0.00006104526,0.00002241636,0.00008245681,0.0001087446,0.00006225805],"domain_scores_gemma":[0.999633,0.0001249602,0.00001649977,0.00008050603,0.00011267,0.00003255354],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004331111,0.0003944142,0.0002804418,0.000236578,0.0001026661,0.000178566,0.00009577541,0.2188181,0.02454909,0.05656125,0.01053537,0.6878147],"study_design_scores_gemma":[0.00001432333,0.00003544199,0.00005644745,0.000009457205,0.00001531152,0.00002401917,0.00001250427,0.9802932,0.004650034,0.01319125,0.001688562,0.000009391863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01346905,0.0002471016,0.9797871,0.0002136185,0.0001099817,0.0000828573,0.0001847977,0.0009452134,0.004960191],"genre_scores_gemma":[0.2692357,0.0003271753,0.7167899,0.0002918633,0.0001013411,0.0002005388,0.0008004475,0.0001781858,0.01207482],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008502202,"threshold_uncertainty_score":0.02844274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03213700420455585,"score_gpt":0.307661566656231,"score_spread":0.2755245624516751,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}