{"id":"W1664525523","doi":"10.1109/ijcnn.2015.7280700","title":"A modular mixed-signal CVNS neural network architecture","year":2015,"lang":"en","type":"article","venue":"","topic":"Numerical Methods and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Modular design; Artificial neural network; Network architecture; Synaptic weight; Flexibility (engineering); Chip; Electronic engineering; Computer hardware; Engineering; Artificial intelligence; Mathematics; Computer network","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":[0.0003492,0.0001219972,0.0001547356,0.00002903023,0.0000601422,0.0001187666,0.0006668657,0.00004022317,0.00002098534],"category_scores_gemma":[0.00002897948,0.00008560287,0.00006929551,0.0004080638,0.00003349911,0.0001453006,0.0002830388,0.0001707152,0.00005137704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001335761,"about_ca_system_score_gemma":0.00003473644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002977979,"about_ca_topic_score_gemma":0.000002206333,"domain_scores_codex":[0.9987644,0.0001598145,0.0001362742,0.000307648,0.000266278,0.0003656099],"domain_scores_gemma":[0.9991793,0.00007784927,0.0000342045,0.0003676115,0.0000481846,0.0002928246],"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":[0.000004550202,0.00003699591,0.0001535448,0.000002212914,0.00001107862,0.00004478921,0.0001418148,0.03097385,0.000173616,0.03525992,0.005279489,0.9279181],"study_design_scores_gemma":[0.0002387485,0.000165641,0.000831575,0.000004669315,0.000003088081,0.00005007737,0.00001120841,0.8266138,0.000270334,0.1407568,0.03083625,0.000217722],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002165523,0.0001367629,0.9917221,0.001935155,0.0007216076,0.00007095403,4.186456e-7,0.0002047718,0.003042722],"genre_scores_gemma":[0.06318761,8.655233e-7,0.9344373,0.001305574,0.0005083722,0.000006244989,5.42138e-7,0.000007575135,0.0005459241],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9277004,"threshold_uncertainty_score":0.3490784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03204978977503297,"score_gpt":0.2698459919056787,"score_spread":0.2377962021306457,"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."}}