{"id":"W6920283708","doi":"10.60692/2gknt-gd342","title":"Reinforced Training Data Selection for Domain Adaptation","year":2019,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Selection (genetic algorithm); Domain (mathematical analysis); Generator (circuit theory); Set (abstract data type); Dependency (UML); Training set; Adaptation (eye); Domain adaptation; Reinforcement learning","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":[0.002493207,0.0008430692,0.001012693,0.0006805404,0.0004062904,0.0005678215,0.001997188,0.0009360157,0.001446793],"category_scores_gemma":[0.008937778,0.0004458859,0.0005860634,0.000594086,0.0009581393,0.001827578,0.001895551,0.002033073,0.0006684287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007078832,"about_ca_system_score_gemma":0.001126079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001839842,"about_ca_topic_score_gemma":0.002804241,"domain_scores_codex":[0.9988276,0.0005012699,0.00005887436,0.0003870384,0.000154961,0.00007036602],"domain_scores_gemma":[0.9968303,0.001730549,0.0001648774,0.0007486732,0.000399197,0.0001265251],"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":[0.0003589717,0.0005710741,0.005940505,0.0001837198,0.0001769457,0.0002040549,0.0003468439,0.419559,0.0220164,0.01246487,0.006115234,0.5320624],"study_design_scores_gemma":[0.00002215778,0.00006140445,0.0004255592,0.000008262042,0.00001277637,0.00004181271,0.00002224873,0.9862956,0.004417381,0.007581633,0.001099446,0.00001171565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03077597,0.0002300951,0.9660293,0.0002031314,0.00004914716,0.0001273724,0.00009338596,0.001595019,0.0008965424],"genre_scores_gemma":[0.7348948,0.0001694628,0.2609395,0.0003866841,0.00006718237,0.0004404115,0.0005847433,0.0002308818,0.002286322],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002493207,"threshold_uncertainty_score":0.0131855,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09651272768991555,"score_gpt":0.2432969266735265,"score_spread":0.1467841989836109,"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."}}