{"id":"W2559852827","doi":"10.1109/tvlsi.2016.2615306","title":"An Analog CVNS-Based Sigmoid Neuron for Precise Neurochips","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","topic":"Analog and Mixed-Signal Circuit Design","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; CMC Microsystems","keywords":"Sigmoid function; Computer science; Artificial neural network; Electronic engineering; Artificial intelligence; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001771563,0.0002016999,0.0001836357,0.000191314,0.0002407,0.00055956,0.0009517763,0.0003800528,0.002327676],"category_scores_gemma":[0.0003877666,0.0001267989,0.0001728879,0.0002798898,0.0002568947,0.0005779736,0.0003530899,0.0003190025,0.0006863438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005191801,"about_ca_system_score_gemma":0.0004602065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001275285,"about_ca_topic_score_gemma":0.002398939,"domain_scores_codex":[0.9998298,0.00002237343,0.00001461863,0.00003526417,0.00007769849,0.00002021464],"domain_scores_gemma":[0.9998504,0.00002317557,0.00001404197,0.00002395159,0.00007797467,0.00001038857],"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":[0.000507574,0.00009130996,0.002080934,0.0007065627,0.0001029818,0.0004406604,0.0002345459,0.09781918,0.4175335,0.05583586,0.005814746,0.4188321],"study_design_scores_gemma":[0.00004806712,0.0006189556,0.002199624,0.0001360339,0.0001026685,0.001021823,0.0001030583,0.658352,0.2631661,0.0100897,0.06409942,0.00006253692],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1115716,0.001406537,0.8627282,0.0004067684,0.0004547152,0.0001071544,0.0002381217,0.001776229,0.02131077],"genre_scores_gemma":[0.8398418,0.0004733926,0.1490542,0.0002012505,0.00003595456,0.00005596526,0.0001108166,0.00004051634,0.01018619],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002327676,"threshold_uncertainty_score":0.00778687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01574964619561676,"score_gpt":0.2281289421108876,"score_spread":0.2123792959152709,"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."}}