{"id":"W2145494108","doi":"","title":"Semi-supervised Learning by Entropy Minimization","year":2004,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1022,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Semi-supervised learning; Machine learning; Computer science; Artificial intelligence; Entropy (arrow of time); Labeled data; Regularization (linguistics); Weighting; Unsupervised learning; Generative grammar; Robustness (evolution); Supervised learning; Mathematics; Pattern recognition (psychology); Artificial neural network","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":[0.004513504,0.001108937,0.002052387,0.001241978,0.0006172754,0.001610145,0.002481254,0.001705143,0.001988703],"category_scores_gemma":[0.01014205,0.0006140173,0.001008839,0.001311442,0.002504795,0.00301839,0.002766563,0.002658991,0.0008975172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007524657,"about_ca_system_score_gemma":0.001001749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005386747,"about_ca_topic_score_gemma":0.0007030301,"domain_scores_codex":[0.9960758,0.002215027,0.0001445632,0.0008003379,0.0006520308,0.000112297],"domain_scores_gemma":[0.9918711,0.005377566,0.0005824936,0.001260004,0.0006846935,0.0002242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001793715,0.0002538723,0.001530675,0.0005502222,0.0003552549,0.0002409264,0.000393918,0.5437194,0.005768457,0.126136,0.007316871,0.313555],"study_design_scores_gemma":[0.000009187069,0.00005031595,0.0001304723,0.00001478241,0.000009858561,0.00005505018,0.00001453339,0.9238861,0.001180628,0.07356033,0.001074265,0.00001454813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00269635,0.0001557611,0.9962475,0.0001454179,0.00002260006,0.00003139256,0.00002719389,0.000141779,0.0005320088],"genre_scores_gemma":[0.3250882,0.000693841,0.6684245,0.0004074581,0.0004599013,0.0004085591,0.00055377,0.0002133413,0.003750492],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004513504,"threshold_uncertainty_score":0.02386999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01020112825328796,"score_gpt":0.2203098783071313,"score_spread":0.2101087500538434,"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."}}