{"id":"W2143293153","doi":"10.1109/ijcnn.1992.226910","title":"A methodology for selection of analog hardware for back-propagation algorithm implementation","year":2003,"lang":"en","type":"article","venue":"","topic":"Analog and Mixed-Signal Circuit Design","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Backpropagation; Computer science; Selection (genetic algorithm); Algorithm; Artificial neural network; Artificial intelligence; Very-large-scale integration; Propagation of uncertainty; Computer engineering; Computer hardware; Embedded system","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001174159,0.0011376,0.0006184298,0.001288704,0.0006628935,0.00174297,0.002057411,0.0007549796,0.01172833],"category_scores_gemma":[0.003393147,0.0006996935,0.0004795929,0.0007741525,0.000705569,0.001286205,0.0009998097,0.001653157,0.004305747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006458918,"about_ca_system_score_gemma":0.001178716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007897896,"about_ca_topic_score_gemma":0.001228229,"domain_scores_codex":[0.9986909,0.0002486399,0.0001120759,0.0001861177,0.0006788525,0.00008348242],"domain_scores_gemma":[0.9986877,0.0003939125,0.0001257618,0.0002732486,0.0004765049,0.00004295678],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001836981,0.0001816424,0.000764198,0.0008630699,0.00009369298,0.0004391409,0.0002197128,0.04042444,0.1520493,0.1192834,0.007728644,0.6777691],"study_design_scores_gemma":[0.0001596277,0.0006507968,0.0009935142,0.0002724339,0.0001213204,0.00198403,0.0001113081,0.4120179,0.327495,0.09298979,0.1630732,0.0001311658],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005302679,0.00005679575,0.9975678,0.0000256295,0.00002256395,0.0001021259,0.00001941261,0.0007251973,0.0009501856],"genre_scores_gemma":[0.02103529,0.0001510892,0.9757079,0.00005892629,0.00002480647,0.0003715521,0.00008374947,0.0002026628,0.002364044],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01172833,"threshold_uncertainty_score":0.03923512,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06344310068286046,"score_gpt":0.3174294650204917,"score_spread":0.2539863643376313,"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."}}