{"id":"W3046517452","doi":"10.1109/tcsi.2020.3010723","title":"Hardware-Algorithm Co-Design of a Compressed Fuzzy Active Learning Method","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems I Regular Papers","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Reduction (mathematics); Algorithm; Fuzzy logic; Cluster analysis; Compressed sensing; Computer engineering; Artificial intelligence; 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":[0.0002190778,0.0001859575,0.0003502321,0.0000703217,0.0002966194,0.0001060437,0.0003301872,0.00009063163,0.000007700727],"category_scores_gemma":[0.000005004598,0.0001693239,0.0001030775,0.0003876009,0.0000599581,0.0001801638,0.000002838348,0.0002753325,0.000007570402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002133531,"about_ca_system_score_gemma":0.00004573858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003094803,"about_ca_topic_score_gemma":4.975061e-7,"domain_scores_codex":[0.9983768,0.0003307636,0.0003074146,0.0004738502,0.0002897181,0.0002214055],"domain_scores_gemma":[0.9989779,0.00027555,0.0001512859,0.0002853965,0.00007396356,0.0002359249],"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":[0.00001402819,0.00009034763,0.000001572995,0.00009151382,0.0001640611,0.00001080276,0.001892056,0.3939544,0.1012226,0.002544458,0.0002583855,0.4997558],"study_design_scores_gemma":[0.0007824582,0.0004072356,0.00003393361,0.0001012972,0.00005249502,0.00004879677,0.000564302,0.962656,0.02574329,0.00007563591,0.009177851,0.000356755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002030321,0.0001355456,0.9975576,0.0004719499,0.0001611638,0.000490868,0.00002211898,0.0001455153,0.0008121771],"genre_scores_gemma":[0.9913626,0.00009743233,0.007892392,0.0001986905,0.00006262821,0.0000908953,0.000002327663,0.00002120793,0.0002718226],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9911596,"threshold_uncertainty_score":0.690483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03658260580358209,"score_gpt":0.2610879669025987,"score_spread":0.2245053610990166,"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."}}