{"id":"W3206990726","doi":"10.1145/3487025","title":"Adaptive Computation Reuse for Energy-Efficient Training of Deep Neural Networks","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Embedded Computing Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Computation; Speedup; Operand; Artificial neural network; Inference; Efficient energy use; Computer engineering; Reuse; Deep neural networks; Energy (signal processing); Artificial intelligence; Parallel computing; Algorithm; Computer hardware","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004521932,0.0007185784,0.0003754635,0.0004573489,0.0003682242,0.000459575,0.001648097,0.0002785863,0.002689209],"category_scores_gemma":[0.001467944,0.0002723072,0.0003682124,0.0006627123,0.0003677133,0.001341617,0.0008279316,0.0006939218,0.0004886818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006709226,"about_ca_system_score_gemma":0.0009726709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002551974,"about_ca_topic_score_gemma":0.007683193,"domain_scores_codex":[0.9996463,0.00005529928,0.00003305663,0.00007069662,0.0001143372,0.00008041105],"domain_scores_gemma":[0.999496,0.0001596731,0.00005774314,0.0001384258,0.0001196746,0.00002847498],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008385265,0.0002285072,0.004019449,0.0004372806,0.0001090717,0.0003408789,0.000271336,0.327498,0.08728782,0.02119155,0.007675561,0.550102],"study_design_scores_gemma":[0.00003574251,0.0001954387,0.0005700423,0.00002598533,0.00003555783,0.0000920848,0.00004963463,0.9470503,0.03763053,0.008812233,0.005486019,0.00001643722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2068375,0.002808861,0.776509,0.0004404896,0.0002016502,0.00009173442,0.0002076595,0.003711117,0.009191898],"genre_scores_gemma":[0.8377691,0.0004585605,0.1584458,0.0001404281,0.00003517842,0.00008924274,0.0002835579,0.0001912316,0.002586898],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002689209,"threshold_uncertainty_score":0.008996308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03808900066656054,"score_gpt":0.281637279435358,"score_spread":0.2435482787687975,"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."}}