{"id":"W2613903212","doi":"10.1109/globalsip.2017.8309150","title":"A feature embedding strategy for high-level CNN representations from multiple convnets","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Computer science; Embedding; Normalization (sociology); Convolutional neural network; Feature extraction; Principal component analysis; Feature (linguistics); Feature vector; Exploit; Contextual image classification; Image (mathematics)","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":[0.0002773675,0.0008660764,0.0003593414,0.0004070154,0.0001683217,0.0003474044,0.000666326,0.0003993398,0.001695539],"category_scores_gemma":[0.0005849013,0.0002300272,0.0005364068,0.0004061942,0.0002860872,0.001118258,0.0007360967,0.0007985887,0.000533919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003330161,"about_ca_system_score_gemma":0.0003190074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001376804,"about_ca_topic_score_gemma":0.002489903,"domain_scores_codex":[0.99985,0.00002028093,0.00001202918,0.00004760562,0.0000487604,0.00002121499],"domain_scores_gemma":[0.9998575,0.00001992534,0.00002017897,0.00003974526,0.00005103923,0.00001166566],"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":[0.0001515636,0.0001685148,0.001149863,0.000139873,0.0001178254,0.0001712352,0.00008127563,0.19661,0.1138641,0.02101548,0.003141677,0.6633886],"study_design_scores_gemma":[0.000007879137,0.0001274186,0.0007032421,0.00001092536,0.00002764966,0.0001283182,0.00001523442,0.9641804,0.02680705,0.005296862,0.002681706,0.00001342072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02847657,0.0001422819,0.9690782,0.00006180801,0.00003357416,0.0000397432,0.00005840352,0.0006397333,0.001469685],"genre_scores_gemma":[0.5723673,0.0001929053,0.4217528,0.00009568359,0.00003150129,0.000132371,0.0004408698,0.0001184783,0.004868124],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001695539,"threshold_uncertainty_score":0.005672157,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09048114161378658,"score_gpt":0.3638573489804966,"score_spread":0.27337620736671,"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."}}