{"id":"W2122970629","doi":"10.1109/icdar.2009.144","title":"Error-Correcting Output Coding for the Convolutional Neural Network for Optical Character Recognition","year":2009,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Convolutional neural network; Optical character recognition; Hamming distance; Coding (social sciences); Artificial intelligence; Convolutional code; Character (mathematics); Pattern recognition (psychology); Speech recognition; Error detection and correction; Segmentation; Code (set theory); Algorithm; Image (mathematics); Decoding methods; Mathematics","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":[0.0007737363,0.0001495921,0.0001593986,0.00005401492,0.0004624202,0.0002379408,0.0004234667,0.00009818204,0.00002599502],"category_scores_gemma":[0.0002310192,0.0001112687,0.0001510473,0.0001640376,0.00003678498,0.0004965059,0.00005118626,0.0001657271,0.0000218906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004315386,"about_ca_system_score_gemma":0.00003585368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003190469,"about_ca_topic_score_gemma":0.000004128756,"domain_scores_codex":[0.998706,0.00003228799,0.0003041413,0.0003522506,0.0001699299,0.0004354102],"domain_scores_gemma":[0.9981022,0.001235433,0.0001065379,0.000217651,0.000266919,0.00007123446],"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":[0.00003549433,0.00004164276,0.00003475702,0.000007393856,0.00001496634,7.396603e-7,0.00007212275,0.00003499535,0.0003021667,0.02191166,0.01583819,0.9617059],"study_design_scores_gemma":[0.001203373,0.0007576482,0.004055788,0.00009617957,0.00005456963,0.0001522757,0.00007685567,0.8653061,0.01408928,0.09797247,0.01558775,0.0006476699],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003302299,0.00003151535,0.9875294,0.005888437,0.0007345993,0.0009896022,0.00001341184,0.0005407513,0.0009700086],"genre_scores_gemma":[0.5955796,0.000008303094,0.3955613,0.0065019,0.001302159,0.0004024966,0.00007440992,0.00001527184,0.0005545156],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9610582,"threshold_uncertainty_score":0.4537407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06071115328930404,"score_gpt":0.2935590856141292,"score_spread":0.2328479323248251,"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."}}