{"id":"W7051682040","doi":"","title":"Optimization of neural networks by reducing floating- point precision of weights during training","year":2021,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Electrostatic Discharge in Electronics","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial neural network; Range (aeronautics); Process (computing); Focus (optics); Table (database); Point (geometry); Representation (politics); Accuracy and precision","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006381425,0.0007984216,0.001176855,0.0004148764,0.0003626252,0.00005653671,0.0005457156,0.0007724495,0.0001688998],"category_scores_gemma":[0.0005549069,0.0009511312,0.0003768212,0.0009166763,0.00003857738,0.0006827326,0.000069906,0.00174323,0.000002462109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006037366,"about_ca_system_score_gemma":0.00006220386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007319452,"about_ca_topic_score_gemma":0.0001207309,"domain_scores_codex":[0.9953812,0.0002393396,0.001775334,0.0008111594,0.0008307369,0.0009621938],"domain_scores_gemma":[0.9974691,0.0003097456,0.0008379091,0.0006963125,0.0004855561,0.0002013463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009613359,0.00008480083,0.000003762753,0.0009513813,0.0002886262,0.00001235262,0.000112753,0.7223821,0.2427708,0.00182569,0.000005235155,0.03146638],"study_design_scores_gemma":[0.0009292024,0.0001907068,0.00004301103,0.002089106,0.0002737329,0.00003271898,0.0005183491,0.3030281,0.6906646,0.0009727092,0.0001747936,0.001082991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9859359,0.002721161,0.0001118388,0.000002517387,0.001171238,0.0005842875,0.0003254773,0.0003072427,0.008840307],"genre_scores_gemma":[0.9900601,0.0009216442,0.005383401,0.000008936967,0.0000568072,0.00004881141,0.002463686,0.000393707,0.0006629283],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4478938,"threshold_uncertainty_score":0.9992939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007365230310626291,"score_gpt":0.21076161117777,"score_spread":0.2033963808671437,"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."}}