{"id":"W1666587748","doi":"10.1109/mwscas.1992.271156","title":"A VLSI neural network design approach using a priori knowledge","year":2003,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"A priori and a posteriori; Computer science; Artificial neural network; Very-large-scale integration; Table (database); Implementation; Artificial intelligence; Content-addressable memory; Lookup table; Value (mathematics); Machine learning; Computer engineering; Theoretical computer science; Data mining; Programming language; Embedded system","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":[0.0002800825,0.0004427369,0.000294594,0.0003766919,0.0002456305,0.001050275,0.001069558,0.0007245803,0.00558506],"category_scores_gemma":[0.000655622,0.0002780763,0.000340215,0.0003384397,0.0003215031,0.001119433,0.0003149252,0.000622434,0.001498287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006449558,"about_ca_system_score_gemma":0.0007408494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001858231,"about_ca_topic_score_gemma":0.003923969,"domain_scores_codex":[0.9997891,0.00003642198,0.00001560143,0.00005351821,0.00008709168,0.00001830319],"domain_scores_gemma":[0.9998115,0.00005719933,0.00001540476,0.00002791285,0.00008219283,0.000005831533],"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":[0.0001181775,0.00006979705,0.0006640892,0.0004570717,0.0001275283,0.0002345451,0.0001200196,0.3403984,0.05246297,0.1165011,0.006759341,0.482087],"study_design_scores_gemma":[0.00002763882,0.0001610273,0.0002683163,0.00006080531,0.00006403374,0.000228746,0.00002173241,0.9137611,0.01992363,0.03263545,0.0328235,0.00002405561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002244686,0.0003697275,0.989657,0.0001518091,0.0000501263,0.00003283015,0.00004613625,0.0004364318,0.007011266],"genre_scores_gemma":[0.1955895,0.001303797,0.7868047,0.0003721352,0.0001291307,0.0002216472,0.0002579842,0.00008896706,0.01523202],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00558506,"threshold_uncertainty_score":0.01868391,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07650081984100482,"score_gpt":0.281699450044968,"score_spread":0.2051986302039632,"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."}}