{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005792249,0.001040917,0.000517879,0.0003010644,0.0003348661,0.0009619078,0.0007924349,0.0008866392,0.003707351],"category_scores_gemma":[0.004204561,0.0005902107,0.0003985592,0.0003888312,0.0003641182,0.001055226,0.0006837307,0.001390696,0.0007957504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000684276,"about_ca_system_score_gemma":0.0008091045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009750845,"about_ca_topic_score_gemma":0.01229266,"domain_scores_codex":[0.9997999,0.00004910186,0.00001608729,0.00006018008,0.0000390291,0.00003575403],"domain_scores_gemma":[0.9991273,0.000515761,0.0000611632,0.00007919168,0.0001906485,0.00002578486],"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":[0.00008765823,0.00004827181,0.0004140328,0.0000535104,0.00003615492,0.00003564799,0.00004595743,0.8228897,0.006650776,0.001476126,0.001748726,0.1665135],"study_design_scores_gemma":[0.00001103534,0.00002597226,0.000165622,0.00001228066,0.00001090698,0.000008593698,0.000007601833,0.9947968,0.003557596,0.0009480935,0.0004523092,0.000003277484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1063262,0.001037005,0.8804156,0.0004905697,0.0002391392,0.00007860715,0.0001186714,0.002303437,0.008990662],"genre_scores_gemma":[0.6300645,0.0005266828,0.3574984,0.0002333626,0.00008374832,0.0001801171,0.0002939715,0.0005389748,0.01058027],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009750845,"threshold_uncertainty_score":0.0193882,"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."}}