{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002154953,0.000379001,0.0002597284,0.0004545358,0.0002474225,0.0006207873,0.001262129,0.0003231039,0.005023924],"category_scores_gemma":[0.0007312023,0.0002095989,0.0002041675,0.0004670789,0.0001508948,0.0008546464,0.0003738238,0.0003667933,0.001074348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000541205,"about_ca_system_score_gemma":0.0005377597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009781958,"about_ca_topic_score_gemma":0.002106599,"domain_scores_codex":[0.9997268,0.00003634865,0.00002808383,0.00004147418,0.0001186983,0.00004849743],"domain_scores_gemma":[0.999733,0.00006791097,0.00003586145,0.00005304287,0.00009773734,0.00001240443],"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":[0.0005453755,0.000155409,0.001776876,0.0005855304,0.0001148302,0.0004078916,0.0001646477,0.06303184,0.2662834,0.02432035,0.008569126,0.6340447],"study_design_scores_gemma":[0.0001326054,0.000814417,0.002796663,0.0000899609,0.0001019369,0.0009013201,0.00009253895,0.6503589,0.3020072,0.01063367,0.0320148,0.00005610828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1299448,0.001278612,0.846813,0.0004238599,0.000243567,0.0001423631,0.0002435485,0.0059904,0.0149197],"genre_scores_gemma":[0.7331586,0.0003972881,0.2593805,0.0001804179,0.00004912045,0.0001214621,0.0002995511,0.00008538237,0.006327563],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005023924,"threshold_uncertainty_score":0.01680672,"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."}}