{"id":"W2283608423","doi":"10.1109/tsc.2015.2497705","title":"Deep Computation Model for Unsupervised Feature Learning on Big Data","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Services Computing","topic":"Tensor decomposition and applications","field":"Mathematics","cited_by":151,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Francis Xavier University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Computer science; Deep learning; Artificial intelligence; Feature vector; Big data; Tensor (intrinsic definition); Data modeling; Feature (linguistics); Pattern recognition (psychology); Autoencoder; Computation; Feature learning; Machine learning; Data mining; Algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003130082,0.0002193679,0.0002374432,0.0001483829,0.0004874653,0.0001127513,0.0004242036,0.0001186407,0.000004277739],"category_scores_gemma":[0.000007708683,0.0002218468,0.00008602383,0.000275813,0.00001915605,0.0001505345,0.000007093954,0.0003504943,0.00004245756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006594015,"about_ca_system_score_gemma":0.00003990635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001193332,"about_ca_topic_score_gemma":0.00008936493,"domain_scores_codex":[0.9986089,0.00007301666,0.0003055087,0.0004744219,0.0002835595,0.0002546355],"domain_scores_gemma":[0.9984612,0.0004992023,0.0001579576,0.0005167339,0.0002172882,0.0001475652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007005454,0.0002818372,0.000004342568,0.0001151279,0.00004722681,5.896964e-7,0.001834193,0.9532151,0.0002579592,0.0008181647,0.0003724872,0.04298297],"study_design_scores_gemma":[0.001086136,0.00008848603,0.000007944555,0.00009392881,0.00007331492,0.000006408893,0.0007511956,0.9905558,0.0004518152,0.006222681,0.0004363305,0.0002260248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03738101,0.00001053762,0.9601305,0.0007519748,0.0003161597,0.0004947248,0.00006320507,0.0004374112,0.0004144627],"genre_scores_gemma":[0.890043,0.000002322827,0.1088304,0.0005382014,0.0001549342,0.00002577963,0.0001450227,0.00005027417,0.0002101329],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.852662,"threshold_uncertainty_score":0.9046652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1697865211088342,"score_gpt":0.3558426370773456,"score_spread":0.1860561159685115,"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."}}