{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001444709,0.0002154417,0.0002109743,0.00006370388,0.0004845987,0.0001162488,0.0006994642,0.00006908314,0.00000330566],"category_scores_gemma":[0.00002326149,0.0002386081,0.00009727899,0.0007969326,0.00004507933,0.0001602545,0.0002445478,0.0001577521,0.0001301012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007958038,"about_ca_system_score_gemma":0.00005971877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.376926e-7,"about_ca_topic_score_gemma":9.768864e-7,"domain_scores_codex":[0.9983552,0.00002498983,0.0004079157,0.0007151033,0.0001474643,0.0003493607],"domain_scores_gemma":[0.9983896,0.0006352511,0.0002009495,0.0004466973,0.000132582,0.0001948944],"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":[0.00002303922,0.000139022,0.00007344264,0.00008915729,0.00001941869,3.787993e-7,0.0007488803,0.09254397,0.006359769,0.3854023,0.001110845,0.5134897],"study_design_scores_gemma":[0.0003366238,0.00003449495,0.0001292613,0.00001147024,0.00001255408,0.00000141167,0.00001820351,0.9425738,0.003532497,0.008839277,0.04423575,0.0002746475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005976595,0.00009070157,0.9941563,0.001624957,0.00007618919,0.001591092,0.00000612911,0.0007527,0.001104281],"genre_scores_gemma":[0.6689321,0.000001479484,0.3294125,0.0009389322,0.0002790107,0.0003514708,0.00005743692,0.00002192356,0.000005042462],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8500298,"threshold_uncertainty_score":0.9730154,"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."}}