{"id":"W1920065104","doi":"10.1109/iscas.1993.394238","title":"A design method for multilayer feedforward neural networks for simple hardware implementation","year":2002,"lang":"en","type":"article","venue":"1993 IEEE International Symposium on Circuits and Systems","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Artificial neural network; Feed forward; Feedforward neural network; Quantization (signal processing); Sigmoid function; Simple (philosophy); Computer hardware; Layer (electronics); Algorithm; Artificial intelligence; Computer engineering; Control 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":[0.0005465819,0.0008846228,0.0002972259,0.000483895,0.0004189145,0.0005311004,0.0009362953,0.0006547172,0.008664396],"category_scores_gemma":[0.00123338,0.0004639511,0.0004877982,0.0003269291,0.0003059142,0.0007585291,0.0004537613,0.0009265274,0.002500361],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004494997,"about_ca_system_score_gemma":0.0005251732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009104091,"about_ca_topic_score_gemma":0.0019144,"domain_scores_codex":[0.9996585,0.00007276116,0.00002618111,0.00005364238,0.0001694439,0.00001944201],"domain_scores_gemma":[0.9997326,0.00008203639,0.00002841262,0.00003534015,0.0001110859,0.00001063266],"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":[0.0001124679,0.00005743869,0.0003016302,0.0007206206,0.0001025105,0.0002479518,0.0001612777,0.1356791,0.09935632,0.06767641,0.008496061,0.6870882],"study_design_scores_gemma":[0.00006694198,0.0002283568,0.0002726029,0.0001207459,0.00005985831,0.0004537539,0.00002215455,0.853112,0.04497642,0.02463189,0.07600947,0.00004584172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003224324,0.00005597716,0.9984027,0.00002045581,0.00002839226,0.00002570926,0.00001307959,0.0003144546,0.0008168233],"genre_scores_gemma":[0.03158361,0.0001898959,0.9624971,0.00006419529,0.00004597922,0.0003452338,0.00006005211,0.0001269715,0.005086969],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008664396,"threshold_uncertainty_score":0.02898532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07475573353588333,"score_gpt":0.3348145455271668,"score_spread":0.2600588119912834,"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."}}