{"id":"W1981364124","doi":"10.1109/reconfig.2011.79","title":"Resource Efficient Arithmetic Effects on RBM Neural Network Solution Quality Using MNIST","year":2011,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"MNIST database; Computer science; Field-programmable gate array; Artificial neural network; Digital signal processing; Floating point; Computer engineering; Parallel computing; Deep learning; Computer hardware; Algorithm; Artificial intelligence","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":[0.002740518,0.0005766296,0.0004577868,0.0004992699,0.0004030158,0.0008821608,0.0009025859,0.0008213635,0.002842525],"category_scores_gemma":[0.01682107,0.0002374661,0.0002663161,0.0005546221,0.0007400789,0.001539991,0.0009094636,0.001147586,0.0003296083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001031615,"about_ca_system_score_gemma":0.0008493164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006942612,"about_ca_topic_score_gemma":0.008880306,"domain_scores_codex":[0.9991716,0.0002811025,0.00007118651,0.0001458605,0.000235179,0.00009510821],"domain_scores_gemma":[0.994476,0.00421583,0.0002450708,0.0005850913,0.0004126123,0.00006551867],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006928754,0.00009740876,0.002468775,0.0002303982,0.0000527848,0.0001430068,0.0001438069,0.8298137,0.007264594,0.007510956,0.001736863,0.1498448],"study_design_scores_gemma":[0.00002987854,0.0001966294,0.0007277605,0.00003070429,0.00001790531,0.00004939904,0.00005019017,0.9830004,0.01163998,0.003316832,0.0009283129,0.00001211506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7343717,0.003172485,0.2399538,0.001681327,0.0002216925,0.00008595364,0.000327219,0.003132252,0.01705368],"genre_scores_gemma":[0.9349192,0.0002898638,0.06318349,0.0001119786,0.00001452078,0.00003420429,0.0002003578,0.0001323607,0.001114091],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006942612,"threshold_uncertainty_score":0.01449341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05547931979710371,"score_gpt":0.264163443107614,"score_spread":0.2086841233105103,"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."}}