{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001756246,0.0004145791,0.0005144553,0.0001143495,0.0002493489,0.0001193572,0.001303427,0.0003373261,0.00001840686],"category_scores_gemma":[0.00004095848,0.0004012232,0.000340158,0.00004610378,0.00007049099,0.00009353841,0.0004298944,0.0004429294,0.0001771607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004134011,"about_ca_system_score_gemma":0.00005251044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":1.197662e-7,"about_ca_topic_score_gemma":0.0000236855,"domain_scores_codex":[0.9980298,0.00001547714,0.0004674715,0.0007890096,0.0002416315,0.0004565796],"domain_scores_gemma":[0.9969506,0.001268714,0.0002847419,0.00122547,0.0001283723,0.0001420665],"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":[0.00001336661,0.00000236815,2.168647e-7,0.00002144781,0.00003755696,0.000008604455,0.00002439309,0.0005385223,0.000001497485,0.12465,0.001474704,0.8732274],"study_design_scores_gemma":[0.0004227271,0.00005869669,6.599485e-7,0.0001126902,0.00003745833,0.000008657201,5.949389e-7,0.01519006,0.0000233145,0.1719891,0.81176,0.0003960542],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[1.263115e-7,0.0005679182,0.4479956,0.0003647996,0.0006406414,0.00103164,0.000006593719,0.0004126784,0.54898],"genre_scores_gemma":[0.00007048339,0.0003129029,0.02247575,0.001418329,0.0009538651,0.0005599993,0.00002550579,0.0001096765,0.9740735],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8728313,"threshold_uncertainty_score":0.999844,"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."}}