{"id":"W1789445635","doi":"10.1109/ictta.2004.1307859","title":"Reinforcement learning for parameter control of text detection in images from video sequences","year":2004,"lang":"en","type":"preprint","venue":"","topic":"Currency Recognition and Detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Task (project management); Focus (optics); Machine learning; Image (mathematics); Search engine indexing; State (computer science); Contextual image classification; Pattern recognition (psychology); State space; Fuzzy logic; Computer vision; Mathematics; Algorithm","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":[],"consensus_categories":[],"category_scores_codex":[0.0002980182,0.0001825549,0.0003054182,0.0002603869,0.00005049849,0.0001256416,0.0003096473,0.0001801584,0.00005756839],"category_scores_gemma":[0.0001972199,0.0001706962,0.000168797,0.0001462636,0.00003472851,0.0002461974,0.0001567675,0.0003519892,0.00001332903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001346171,"about_ca_system_score_gemma":0.0001133651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001789506,"about_ca_topic_score_gemma":0.0002585279,"domain_scores_codex":[0.998539,0.00007602363,0.0005016545,0.000486415,0.0002139866,0.0001828698],"domain_scores_gemma":[0.9989136,0.0002954414,0.0003285477,0.0002718719,0.0001490349,0.00004143135],"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":[0.000154184,0.00009952963,0.0004461494,0.0002477474,0.0001027424,0.000002983132,0.0007908476,0.3654592,0.01279562,0.0005591966,0.0000264878,0.6193153],"study_design_scores_gemma":[0.001878651,0.0003308846,0.001277694,0.0003220889,0.00002812983,0.000002878822,0.00006466317,0.7828604,0.1617733,0.05081527,0.0002601162,0.0003858913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01694093,0.0001157977,0.980563,0.0001122313,0.0008146225,0.0006478168,0.000006576005,0.0001218605,0.0006771683],"genre_scores_gemma":[0.9895467,0.00004659005,0.009923676,0.00007256108,0.00005917442,0.0002295683,0.00001766197,0.000006903387,0.00009721587],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9726057,"threshold_uncertainty_score":0.6960788,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02684909454203981,"score_gpt":0.2720564803280526,"score_spread":0.2452073857860128,"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."}}