{"id":"W3044911731","doi":"10.1007/978-3-030-58539-6_33","title":"A Unifying Mutual Information View of Metric Learning: Cross-Entropy vs. Pairwise Losses","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Face recognition and analysis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Pairwise comparison; Mutual information; Cross entropy; Entropy (arrow of time); Upper and lower bounds; Heuristics; Discriminative model; Computer science; Mathematics; Metric (unit); Mathematical optimization; Artificial intelligence; Principle of maximum entropy; Engineering","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00110519,0.0003783279,0.0006480163,0.00151471,0.000224806,0.001396156,0.003024175,0.0002164658,0.0000205994],"category_scores_gemma":[0.001099969,0.0003453481,0.0002507005,0.006041049,0.000435856,0.001519236,0.003190846,0.001103375,0.00005841345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001818812,"about_ca_system_score_gemma":0.0007189915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008895265,"about_ca_topic_score_gemma":0.000009985665,"domain_scores_codex":[0.9964002,0.0001959836,0.0008273569,0.0009231959,0.001143206,0.000509994],"domain_scores_gemma":[0.9973598,0.0004439034,0.0006340382,0.0007784241,0.0005847943,0.000199087],"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":[0.000007248731,0.00004452785,0.002675771,0.0003055442,0.00002146162,0.00001151863,0.001862157,0.4250338,0.0001186217,0.0002632145,0.000006431677,0.5696497],"study_design_scores_gemma":[0.0002758396,0.0001212656,0.002122119,0.0002831497,0.00001459791,0.00001051965,0.000001977466,0.984413,0.00616002,0.005895521,0.0003167981,0.0003851351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0132363,0.0003583934,0.9835594,0.001538627,0.0008041349,0.0002649953,0.000005573858,0.0002019901,0.0000306289],"genre_scores_gemma":[0.7848593,0.0001301459,0.2139771,0.0009114883,0.0000888863,0.000009872972,0.00001527328,0.00000706921,8.921533e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.771623,"threshold_uncertainty_score":0.9998999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02329649942509552,"score_gpt":0.2830448434949603,"score_spread":0.2597483440698648,"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."}}