{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019896,0.0001780289,0.0001687578,0.00006242879,0.0003561928,0.0002595784,0.0003079228,0.00008841271,0.00009915338],"category_scores_gemma":[0.00002377286,0.0001846681,0.0001417821,0.000321391,0.00002371516,0.0005356573,0.00007062699,0.0001610808,0.000341597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002946705,"about_ca_system_score_gemma":0.000004058757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001180435,"about_ca_topic_score_gemma":0.0000178117,"domain_scores_codex":[0.9985085,0.00005879256,0.0003193636,0.0004840686,0.0001714043,0.0004578381],"domain_scores_gemma":[0.9991313,0.0001698091,0.0001566144,0.0002853945,0.0001503276,0.0001065606],"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":[0.000002916639,0.00004730313,0.0001669734,0.00001977749,0.00001039456,0.000002638725,0.00004644932,0.000201413,0.0002262406,0.00004880309,0.005105293,0.9941218],"study_design_scores_gemma":[0.0008290636,0.0001657997,0.0008460669,0.0001310765,0.00003447651,0.00005413362,0.00001596797,0.9686953,0.00100055,0.01909868,0.008657067,0.0004718422],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09982251,0.0001561509,0.894522,0.002927684,0.0005086352,0.0007245909,0.00006093273,0.0003550016,0.0009224517],"genre_scores_gemma":[0.9739223,0.00008334799,0.02132549,0.002428212,0.001353468,0.0005266245,0.0002444849,0.00002828656,0.00008785801],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.99365,"threshold_uncertainty_score":0.7530547,"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."}}