{"id":"W2005443073","doi":"10.1109/hpcsim.2012.6266913","title":"A neural network approach to online Devanagari handwritten character recognition","year":2012,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Devanagari; Computer science; Handwriting; Artificial intelligence; Character (mathematics); Feature extraction; Artificial neural network; Pattern recognition (psychology); Discrete cosine transform; Feature (linguistics); Speech recognition; Set (abstract data type); Character encoding; Handwriting recognition; Character recognition; Mathematics; Image (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":[0.0005325356,0.0002283733,0.0002360343,0.0001816787,0.0001357177,0.0002056154,0.0006587041,0.0001192689,0.0001029204],"category_scores_gemma":[0.00004644383,0.0001999814,0.0000988674,0.0006931571,0.0000240125,0.001363454,0.0003497399,0.0002262144,0.0006768159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004820905,"about_ca_system_score_gemma":0.00002004914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002399897,"about_ca_topic_score_gemma":0.000008335569,"domain_scores_codex":[0.9980652,0.000119215,0.0003373698,0.0004299894,0.0002984534,0.0007498129],"domain_scores_gemma":[0.9988118,0.00006394691,0.00008025852,0.0005084375,0.0001524471,0.0003830681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001786212,0.0008141627,0.00189929,0.00002583107,0.00003820097,0.000003759997,0.0006627286,0.000009888738,0.00064475,0.005462415,0.03834128,0.9520798],"study_design_scores_gemma":[0.004895235,0.001969701,0.2323585,0.0006149889,0.000279184,0.00185178,0.0005763017,0.2084343,0.05796554,0.04548005,0.4359095,0.009665013],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03101438,0.00007424766,0.9386719,0.001369225,0.0005004308,0.0006142198,0.00001207722,0.001408062,0.02633539],"genre_scores_gemma":[0.3833116,0.00001184717,0.6057704,0.008726875,0.001077055,0.0001430292,0.0001116269,0.00002561146,0.000821949],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9424148,"threshold_uncertainty_score":0.8699324,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04082976831277993,"score_gpt":0.2630173403252038,"score_spread":0.2221875720124239,"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."}}