{"id":"W2010395010","doi":"10.1109/newcas.2012.6328941","title":"Efficient hardware implementation of threshold neural networks","year":2012,"lang":"en","type":"article","venue":"","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Activation function; Artificial neural network; Very-large-scale integration; Sigmoid function; Hyperbolic function; Process (computing); Hardware architecture; Performance metric; Metric (unit); CMOS; Computer hardware; Computer engineering; Embedded system; Software; Artificial intelligence; Mathematics; Electronic engineering; Engineering","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":[0.0002029484,0.00005019197,0.00005948579,0.00003034586,0.00004350643,0.00002123164,0.0002066025,0.00001607588,0.00009122014],"category_scores_gemma":[0.000003051299,0.00003919981,0.00003082676,0.0001284987,0.000007936866,0.00007886808,0.0001052569,0.00004591931,0.00001041778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006772091,"about_ca_system_score_gemma":0.000005085598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007285317,"about_ca_topic_score_gemma":0.000005252168,"domain_scores_codex":[0.9994587,0.00002256203,0.0001107115,0.00008845659,0.0001225418,0.0001970381],"domain_scores_gemma":[0.9996739,0.00001804995,0.00004448343,0.0001901618,0.00002059588,0.00005279328],"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":[0.000004826218,0.0001658325,0.2810875,0.00002051504,0.00002198234,0.000001201455,0.002942224,0.2957472,0.0002990484,0.10926,0.004996756,0.3054529],"study_design_scores_gemma":[0.0001293188,0.00002698878,0.05643908,0.000001499986,0.000002059097,0.000002559765,0.00005349104,0.9423949,0.000380689,0.00001655859,0.0004982509,0.00005460711],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4251913,0.00009464136,0.5712274,0.0003599988,0.0003437201,0.00005376702,2.417266e-7,0.0000835578,0.002645359],"genre_scores_gemma":[0.9966912,5.770254e-7,0.002928287,0.000175109,0.00007270982,0.000002277352,0.000001522514,0.000002689782,0.0001256677],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6466478,"threshold_uncertainty_score":0.1598522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01469240805026793,"score_gpt":0.289108562683541,"score_spread":0.274416154633273,"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."}}