{"id":"W2996690709","doi":"10.1109/aicas48895.2020.9073854","title":"Layerwise Noise Maximisation to Train Low-Energy Deep Neural Networks","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données","keywords":"Overhead (engineering); Reliability (semiconductor); Computer science; Artificial neural network; Energy (signal processing); Stochastic gradient descent; Inference; Energy consumption; Deep neural networks; Noise (video); Exponential function; Layer (electronics); Algorithm; Artificial intelligence; Statistics; Engineering; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001020758,0.0004714699,0.0004093463,0.0001298323,0.0001474956,0.0003143314,0.002430586,0.000263021,0.00003947254],"category_scores_gemma":[0.000038208,0.0004810005,0.0001930444,0.0008287468,0.00003653017,0.0002737284,0.002722046,0.0006460879,0.00007487663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001236705,"about_ca_system_score_gemma":0.00005964295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006220709,"about_ca_topic_score_gemma":0.000122716,"domain_scores_codex":[0.9969746,0.0001047498,0.0005330972,0.001462661,0.0003752624,0.0005495838],"domain_scores_gemma":[0.9973834,0.0001555308,0.0002261646,0.001600984,0.0001235652,0.0005103301],"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":[0.000008492885,0.00003244344,0.000009004048,0.00001227124,0.0000123863,0.00001329482,0.0001520012,0.8067396,0.0001813951,0.04030627,0.003339448,0.1491934],"study_design_scores_gemma":[0.0001315814,0.00003614629,0.0002707092,0.00001676604,0.000009988689,0.000006990547,0.000006421266,0.970474,0.0002432553,0.02550079,0.002804683,0.0004986838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004977913,0.0001342524,0.9759204,0.0196113,0.0007148489,0.0006024218,0.000005560354,0.00100105,0.001512313],"genre_scores_gemma":[0.7906879,0.00004459159,0.1962885,0.01108937,0.0008267289,0.0005556042,0.00009260153,0.00006000492,0.0003547651],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.79019,"threshold_uncertainty_score":0.9997641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02502243469470757,"score_gpt":0.2590967731519528,"score_spread":0.2340743384572453,"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."}}