{"id":"W4383566636","doi":"10.1016/b978-0-12-805320-1.00015-4","title":"Constrained deep networks","year":2023,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Prior probability; Regularization (linguistics); Artificial intelligence; Computer science; Segmentation; Context (archaeology); Deep learning; Focus (optics); Machine learning; Conditional random field; Mathematical optimization; Mathematics; 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":[0.0002689222,0.001157952,0.0006889326,0.0005172113,0.0002896934,0.001278802,0.0009518535,0.001166658,0.05203379],"category_scores_gemma":[0.001039957,0.0005295078,0.0003960927,0.001018465,0.000404531,0.001664101,0.001401683,0.001885005,0.0269723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005286849,"about_ca_system_score_gemma":0.0005910356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004084831,"about_ca_topic_score_gemma":0.007963559,"domain_scores_codex":[0.9998734,0.0000146714,0.000005230349,0.00004967066,0.00004367748,0.0000133566],"domain_scores_gemma":[0.9997954,0.00006428268,0.000009307387,0.00007014829,0.00004533051,0.00001567831],"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":[0.00003229219,0.00004118709,0.000120824,0.0001691851,0.00003620142,0.00004151729,0.00002439347,0.03567391,0.002944712,0.04701664,0.1659447,0.7479545],"study_design_scores_gemma":[0.0000162146,0.00004156843,0.0006323199,0.0002134804,0.00003978474,0.0001916131,0.00002956771,0.3654614,0.006476264,0.2423111,0.3845493,0.00003738493],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004345014,0.01533109,0.8045959,0.002315341,0.001382715,0.00005287569,0.002298037,0.007221467,0.1624575],"genre_scores_gemma":[0.08038957,0.01493771,0.2661881,0.001137827,0.0009258972,0.0002168815,0.008309545,0.00308604,0.6248085],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05203379,"threshold_uncertainty_score":0.1740704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02177718798286257,"score_gpt":0.2347554361359781,"score_spread":0.2129782481531155,"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."}}