{"id":"W2618636670","doi":"10.1016/j.parco.2017.05.003","title":"Proteus: Exploiting precision variability in deep neural networks","year":2017,"lang":"en","type":"article","venue":"Parallel Computing","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Memory footprint; Inference; Convolutional neural network; Artificial neural network; Proteus; Efficient energy use; Floating point; Computer engineering; Real-time computing; Algorithm; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001253781,0.0002129411,0.0002622346,0.00006114909,0.0009771599,0.0004446374,0.00228705,0.00008247695,0.000003215833],"category_scores_gemma":[0.0005449416,0.0002148033,0.00007160731,0.0002429896,0.00007780045,0.000881516,0.001584884,0.0004514928,0.00001410296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007537979,"about_ca_system_score_gemma":0.00001544993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002969976,"about_ca_topic_score_gemma":0.00002366463,"domain_scores_codex":[0.997655,0.000226919,0.0004944468,0.000788102,0.0002358576,0.0005996415],"domain_scores_gemma":[0.9970263,0.0006651729,0.0004220852,0.00169787,0.00007401592,0.0001145064],"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":[0.00000650558,0.00004481781,0.01214735,0.000007192277,0.000002914838,0.0000108333,0.0002070186,0.6139846,0.00003838084,0.008765785,0.00001582962,0.3647687],"study_design_scores_gemma":[0.0002950244,0.00001737163,0.0337975,0.00003404182,0.00000144417,0.00001151938,0.000007593023,0.9537714,0.00002299795,0.01173148,0.00009534624,0.0002142788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04162401,0.00006128688,0.9550346,0.0006898587,0.0002848627,0.0006270588,1.743464e-7,0.0002496583,0.001428556],"genre_scores_gemma":[0.7886671,0.000004903802,0.2109418,0.0001085762,0.0002081453,0.00004557548,0.000001384501,0.0000131706,0.000009336859],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7470431,"threshold_uncertainty_score":0.8759425,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02995690329559604,"score_gpt":0.3004231432261359,"score_spread":0.2704662399305399,"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."}}