{"id":"W4383566674","doi":"10.1016/b978-0-12-805320-1.00014-2","title":"Random field losses for deep networks","year":2023,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Conditional random field; CRFS; Computer science; Leverage (statistics); Segmentation; Artificial intelligence; Pairwise comparison; Regularization (linguistics); Convolutional neural network; Ground truth; Deep learning; Prior probability; Cluster analysis; Machine learning; Pattern recognition (psychology); Bayesian probability","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":[0.0005392974,0.001080985,0.0006539053,0.0005383036,0.0001585629,0.001093484,0.0009558448,0.001083863,0.03313389],"category_scores_gemma":[0.001663959,0.0004642272,0.0004232333,0.0009480349,0.00041399,0.002208326,0.0008728169,0.002192591,0.01482263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005782121,"about_ca_system_score_gemma":0.0003817376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001425866,"about_ca_topic_score_gemma":0.002350378,"domain_scores_codex":[0.9998048,0.00003393331,0.00001108429,0.00004233213,0.00009190977,0.00001594842],"domain_scores_gemma":[0.9996644,0.0001697675,0.00001904438,0.00006490377,0.00006733655,0.00001454229],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003981705,0.0000452423,0.0001124777,0.0003565788,0.00003379471,0.00004892428,0.00002424351,0.04909423,0.00213051,0.11631,0.1491358,0.6826682],"study_design_scores_gemma":[0.00001780765,0.00005379522,0.0004778611,0.0002345076,0.00002846213,0.0001999889,0.00001650038,0.3767652,0.004029641,0.3826779,0.2354607,0.00003770239],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002586682,0.01920767,0.9012766,0.001937895,0.001505534,0.00003529352,0.001178584,0.003516424,0.06875526],"genre_scores_gemma":[0.08648634,0.03149664,0.4151291,0.001096313,0.002409038,0.0002642333,0.005808694,0.003618974,0.4536907],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03313389,"threshold_uncertainty_score":0.1108439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02207124826446452,"score_gpt":0.2631527858397047,"score_spread":0.2410815375752402,"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."}}