{"id":"W2809703834","doi":"10.1007/978-3-030-00928-1_57","title":"Subject2Vec: Generative-Discriminative Approach from a Set of Image Patches to a Vector","year":2018,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"National Heart, Lung, and Blood Institute","keywords":"Discriminative model; Interpretability; Computer science; Artificial intelligence; Pattern recognition (psychology); Generative model; Context (archaeology); Representation (politics); Generative grammar; Image (mathematics); Set (abstract data type); Machine learning","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":[0.0005869567,0.002119418,0.001433428,0.001583205,0.000473773,0.0008391068,0.001824853,0.001290705,0.007467175],"category_scores_gemma":[0.001327289,0.0006221537,0.001416206,0.002404593,0.0006878174,0.001099112,0.001861405,0.00217323,0.006336862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000553015,"about_ca_system_score_gemma":0.001321521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009340404,"about_ca_topic_score_gemma":0.02158842,"domain_scores_codex":[0.9993759,0.0001034241,0.00002972654,0.0002316405,0.0001707297,0.00008855404],"domain_scores_gemma":[0.9994783,0.00008582923,0.00003502647,0.0001941499,0.0001599088,0.00004682914],"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":[0.0005250577,0.0004252535,0.002308364,0.0004950151,0.0002726808,0.0002552582,0.0001363576,0.028921,0.0468061,0.007357476,0.1293853,0.783112],"study_design_scores_gemma":[0.0001047441,0.0004347826,0.003308909,0.00008845882,0.000165012,0.0007243942,0.0001432564,0.8970554,0.03912646,0.01485907,0.04390863,0.00008097343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02350573,0.001588356,0.9395674,0.0005770463,0.000802656,0.000296175,0.00522577,0.02551474,0.002922074],"genre_scores_gemma":[0.3267465,0.002655866,0.5888472,0.001518315,0.0009000291,0.0009187324,0.03756081,0.004731239,0.03612136],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009340404,"threshold_uncertainty_score":0.02498019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02709640894807332,"score_gpt":0.307665434539398,"score_spread":0.2805690255913247,"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."}}