{"id":"W2165313956","doi":"10.1016/s0031-3203(00)00181-3","title":"A class-modular feedforward neural network for handwriting recognition","year":2002,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Modular neural network; Modular design; Computer science; Neocognitron; Artificial neural network; Modularity (biology); Artificial intelligence; Numeral system; Pattern recognition (psychology); Feedforward neural network; Time delay neural network; Classifier (UML); Intelligent character recognition; Feed forward; Class (philosophy); Handwriting; Character recognition","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":[0.0003069844,0.0005062618,0.000516026,0.0003086936,0.0003510371,0.0004147619,0.0012105,0.0006866594,0.005307259],"category_scores_gemma":[0.0006371457,0.0002013755,0.0004810496,0.0004613665,0.0002430608,0.0007699241,0.0006749288,0.0006935387,0.001395706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003936563,"about_ca_system_score_gemma":0.0004910572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002535613,"about_ca_topic_score_gemma":0.005104027,"domain_scores_codex":[0.9998648,0.00001675978,0.000007295056,0.0000498117,0.00004379806,0.00001752114],"domain_scores_gemma":[0.9998123,0.00004273671,0.00001480769,0.00003617483,0.00007279631,0.00002125214],"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":[0.0002598104,0.00009892791,0.0005119703,0.0001917601,0.00008207217,0.0001213476,0.00004434206,0.08421227,0.0474246,0.01117553,0.007981327,0.847896],"study_design_scores_gemma":[0.00001477709,0.00006221073,0.0003825425,0.00001016483,0.00002875263,0.00007857696,0.000005206054,0.9849888,0.006804029,0.00384544,0.00376949,0.000009872527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01916503,0.0006772737,0.9741741,0.0001714588,0.0002358402,0.00006143123,0.0001930953,0.001774407,0.00354733],"genre_scores_gemma":[0.3879609,0.0007322407,0.5930662,0.0002912372,0.0003090524,0.0001948296,0.0007150083,0.0002652229,0.01646546],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005307259,"threshold_uncertainty_score":0.01775455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06097439202250519,"score_gpt":0.249354875912815,"score_spread":0.1883804838903099,"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."}}