{"id":"W2997288154","doi":"10.1109/robio49542.2019.8961780","title":"Deep Learning Training with Simulated Approximate Multipliers","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Killam Trusts; Dalhousie University","keywords":"Computer science; Convolutional neural network; Approximation error; Artificial neural network; Lagrange multiplier; Speedup; Mathematical optimization; Training (meteorology); Power (physics); Algorithm; Artificial intelligence; Mathematics; Parallel computing","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004625458,0.0004178527,0.0003094451,0.0002326547,0.0001788309,0.000455551,0.0006173895,0.0005512113,0.002278304],"category_scores_gemma":[0.00248641,0.0002288948,0.0002860681,0.0002950105,0.0003814183,0.000695035,0.0003937308,0.0005791462,0.0001976468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006506692,"about_ca_system_score_gemma":0.0005498669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003667791,"about_ca_topic_score_gemma":0.003870364,"domain_scores_codex":[0.9998363,0.0000488552,0.000009160633,0.00002350955,0.00005235587,0.00002980128],"domain_scores_gemma":[0.999096,0.0005913998,0.0000856727,0.00008184394,0.0001228846,0.0000222384],"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":[0.00006968354,0.0000174208,0.00046685,0.0000414495,0.000009793708,0.00003011348,0.00001711232,0.9851917,0.00160084,0.003654788,0.0002265097,0.008673747],"study_design_scores_gemma":[0.000005675111,0.00002657998,0.0000552358,0.000004133553,0.00000250882,0.000007877105,0.000003373405,0.9968546,0.001847787,0.0008924023,0.0002981898,0.00000154976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3235322,0.0006384471,0.6553174,0.0004266453,0.0001486201,0.0001001459,0.0002840112,0.0009638549,0.01858875],"genre_scores_gemma":[0.92742,0.0001219998,0.07024515,0.00006081866,0.000008424863,0.00008300471,0.00008902967,0.00004286659,0.001928665],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003667791,"threshold_uncertainty_score":0.007621646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01586306978373895,"score_gpt":0.240508102606348,"score_spread":0.224645032822609,"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."}}