{"id":"W2063369767","doi":"10.1109/icpr.2010.1043","title":"Applying Error-Correcting Output Coding to Enhance Convolutional Neural Network for Target Detection and Pattern Recognition","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Convolutional neural network; Computer science; Convolutional code; Coding (social sciences); Error detection and correction; Hamming distance; Pattern recognition (psychology); Artificial neural network; Hamming code; Artificial intelligence; Speech recognition; Time delay neural network; Neural coding; Decoding methods; Algorithm; Block code; 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":[0.0002326919,0.0001408967,0.0001225356,0.00005728302,0.000514792,0.0001083699,0.0002349781,0.00006207533,0.000007171636],"category_scores_gemma":[0.0000824116,0.0001480479,0.00003857175,0.0003143488,0.00002585626,0.0004476204,0.0001445964,0.0002324822,0.00001858317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002581139,"about_ca_system_score_gemma":0.0000119237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001490157,"about_ca_topic_score_gemma":0.00017984,"domain_scores_codex":[0.9987505,0.00002275942,0.0002282698,0.0005116875,0.0001242662,0.0003625119],"domain_scores_gemma":[0.9990559,0.0003605578,0.00010897,0.0002311648,0.0001197793,0.0001236645],"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":[0.000008830871,0.00001119618,0.000602703,0.000008194614,0.000004330971,3.684131e-7,0.00007073097,0.004598598,0.018539,0.0004797271,0.0003502936,0.975326],"study_design_scores_gemma":[0.0001664593,0.00007080413,0.001587502,0.00001765948,0.00000546619,0.00005109538,0.0000245621,0.965508,0.01984139,0.008352946,0.004060945,0.0003131188],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08238684,0.00001235478,0.9147602,0.0005600396,0.0009843789,0.0009251981,0.000004342139,0.000261063,0.0001055289],"genre_scores_gemma":[0.7393349,0.00000126945,0.2584729,0.0007993384,0.0004716671,0.0008358177,0.000007367759,0.00001158528,0.00006516358],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9750129,"threshold_uncertainty_score":0.6037216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02850952672682484,"score_gpt":0.2868386141138544,"score_spread":0.2583290873870295,"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."}}