{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000696774,0.0001944388,0.0002185428,0.00005444018,0.0003823832,0.0001271562,0.00046956,0.0000662402,0.00002361606],"category_scores_gemma":[0.00007110502,0.0001590004,0.0001123653,0.0003801541,0.00005187385,0.000142873,0.0002357381,0.0001439947,0.00004095374],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006105824,"about_ca_system_score_gemma":0.00002399035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002590709,"about_ca_topic_score_gemma":0.0000156461,"domain_scores_codex":[0.9979796,0.0005117797,0.0002624396,0.0004896664,0.0002829781,0.0004735467],"domain_scores_gemma":[0.9988906,0.0002391554,0.0001156869,0.0005750706,0.00005634833,0.000123139],"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":[0.0001465109,0.0005227057,0.001125113,0.00005353471,0.00009326002,0.00006014513,0.001481974,0.7524768,0.005891883,0.06402529,0.005386687,0.1687362],"study_design_scores_gemma":[0.0002397483,0.0001557897,0.006385993,0.00002933729,0.00001277947,0.000004674963,0.00001092716,0.9837501,0.008061412,0.0004945774,0.0006090697,0.00024561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04391981,0.00008603295,0.9468544,0.000182746,0.0007605555,0.0002151479,4.278889e-7,0.000148795,0.007832075],"genre_scores_gemma":[0.902284,0.000001051954,0.09646602,0.0007462956,0.000352325,0.00000526574,8.645541e-7,0.00001014128,0.0001339843],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8583642,"threshold_uncertainty_score":0.6483846,"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."}}