{"id":"W2744816398","doi":"10.1145/3063593","title":"A Tucker Deep Computation Model for Mobile Multimedia Feature Learning","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Tensor decomposition and applications","field":"Mathematics","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Computation; Speedup; Computer science; Tucker decomposition; Deep learning; Artificial intelligence; Feature (linguistics); Server; Machine learning; Parallel computing; Algorithm; Tensor (intrinsic definition); Tensor decomposition; Mathematics; Computer network","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":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0003733879,0.0003295415,0.0003638909,0.000189347,0.005633045,0.0003215943,0.001518894,0.0002073746,0.00001304225],"category_scores_gemma":[0.0001828838,0.0003521129,0.0001993491,0.0001745383,0.0004488479,0.0002735924,0.0001267283,0.0006644942,0.00003531119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007250653,"about_ca_system_score_gemma":0.00005528961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000198536,"about_ca_topic_score_gemma":0.00007513147,"domain_scores_codex":[0.9982547,0.00009178994,0.0005132157,0.0005693174,0.0002126353,0.0003582956],"domain_scores_gemma":[0.9934946,0.002409018,0.0004989251,0.002997401,0.0003805982,0.0002195006],"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":[0.00003955207,0.001609939,0.0001881101,0.0001107504,0.0001848804,2.752886e-7,0.002855876,0.01963061,0.001672345,0.01519119,0.0005569882,0.9579595],"study_design_scores_gemma":[0.001112958,0.00005776435,0.0003886897,0.00005223713,0.0001458886,0.00000939162,0.0003371814,0.9644176,0.0001512844,0.02491312,0.00804595,0.0003679016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003943297,0.0001215321,0.9888973,0.003557431,0.00005594943,0.002445373,0.0001375288,0.0004441672,0.000397471],"genre_scores_gemma":[0.5039634,0.0001758596,0.4930842,0.00008969568,0.00006176103,0.002028169,0.0001391136,0.00004814923,0.0004096547],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9575916,"threshold_uncertainty_score":0.9998931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06013025682110174,"score_gpt":0.3723619049408898,"score_spread":0.3122316481197881,"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."}}