{"id":"W163273042","doi":"","title":"A mixed-signal feed-forward neural network architecture with on-chip learning in CMOS 0.18 microns.","year":2003,"lang":"en","type":"article","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"CMOS; Artificial neural network; Computer science; Chip; SIGNAL (programming language); Computer architecture; Artificial intelligence; Electronic engineering; Engineering; Telecommunications","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0002019033,0.0003189079,0.0002138309,0.0002251129,0.0002314394,0.0004396876,0.001204656,0.0004917061,0.003308238],"category_scores_gemma":[0.0002711551,0.0001658407,0.0001844174,0.0001875526,0.0001472768,0.0005867796,0.000304426,0.0003950258,0.0007741075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000554486,"about_ca_system_score_gemma":0.0006216179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003271673,"about_ca_topic_score_gemma":0.008406488,"domain_scores_codex":[0.9998469,0.00002633189,0.000008037837,0.00003105964,0.0000714929,0.00001620266],"domain_scores_gemma":[0.9999124,0.0000142699,0.00001041213,0.00001030986,0.00004410218,0.000008586385],"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":[0.0003555082,0.0002532966,0.001567413,0.0006082873,0.0001412878,0.0004015564,0.0001960736,0.07361948,0.30582,0.01805919,0.01384188,0.5851358],"study_design_scores_gemma":[0.00006900817,0.0008279325,0.001322959,0.000054011,0.00007065435,0.0003737077,0.00004552834,0.8386989,0.1089145,0.002388201,0.04718435,0.00005027365],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08402047,0.003199735,0.8771984,0.000667839,0.0005219811,0.0002802527,0.0003132913,0.006476829,0.02732116],"genre_scores_gemma":[0.4950714,0.0006623172,0.4841614,0.0004605531,0.00005386319,0.0002031402,0.0003259338,0.00007820302,0.01898315],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003308238,"threshold_uncertainty_score":0.01106715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01755019846925974,"score_gpt":0.2023843228346863,"score_spread":0.1848341243654266,"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."}}