{"id":"W2155625967","doi":"10.1109/icpr.1992.201751","title":"A structurally adaptive neural tree for the recognition of large character set","year":2003,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Concordia University","keywords":"Character (mathematics); Computer science; Tree (set theory); Adaptation (eye); Artificial intelligence; Set (abstract data type); Artificial neural network; Parametric statistics; Character recognition; Pattern recognition (psychology); Machine learning; Mathematics; Biology; Image (mathematics); Neuroscience","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000567749,0.0003285053,0.0004248247,0.0008011723,0.0003833844,0.0004282046,0.0008606956,0.0006524778,0.00276647],"category_scores_gemma":[0.001765946,0.0001929275,0.0004815783,0.00134372,0.0002941643,0.001171567,0.0004341597,0.0006701857,0.001166366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003947788,"about_ca_system_score_gemma":0.0004276502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003115051,"about_ca_topic_score_gemma":0.00475079,"domain_scores_codex":[0.999694,0.00006302141,0.00002049657,0.000078079,0.0001151461,0.00002929893],"domain_scores_gemma":[0.9995791,0.0001462478,0.00003189953,0.00005511509,0.000166472,0.00002110481],"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":[0.0001059614,0.00008034152,0.0008724895,0.0001442408,0.00006000557,0.0001503047,0.00009446532,0.1067583,0.0324086,0.01363734,0.007367959,0.8383201],"study_design_scores_gemma":[0.000006165605,0.00005369601,0.0005966781,0.00001221564,0.00001798798,0.0001172597,0.00001292943,0.9795755,0.007375995,0.007377008,0.004839879,0.00001474279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01338074,0.0006111799,0.9821048,0.00009385654,0.00007809252,0.00004757107,0.0001597731,0.001685618,0.001838363],"genre_scores_gemma":[0.1710544,0.0005876811,0.8224766,0.0001511231,0.0000804139,0.0001435838,0.000761435,0.00020071,0.004544038],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003115051,"threshold_uncertainty_score":0.009254754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04427399205650867,"score_gpt":0.2703520017686727,"score_spread":0.226078009712164,"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."}}