{"id":"W2766944760","doi":"10.48550/arxiv.1711.00333","title":"An Experimental Analysis of the Power Consumption of Convolutional Neural Networks for Keyword Spotting","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Keyword spotting; Computer science; Proxy (statistics); Convolutional neural network; Predictive power; Inference; Spotting; Artificial intelligence; Footprint; Artificial neural network; Data mining; Machine learning; Geography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002551645,0.000151801,0.0003338408,0.0002342961,0.0001871311,0.00005034193,0.001399042,0.0001567943,0.00007249169],"category_scores_gemma":[0.00003695686,0.0001443123,0.0005018446,0.0002505993,0.0002138818,0.0002252099,0.0005267645,0.0001556125,0.000001127837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006634729,"about_ca_system_score_gemma":0.0000607089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005050357,"about_ca_topic_score_gemma":0.00001912767,"domain_scores_codex":[0.9989162,0.0001265565,0.0002125424,0.0004880645,0.00009526467,0.0001613896],"domain_scores_gemma":[0.9979904,0.0001543682,0.0006148422,0.0009708231,0.0002060455,0.0000635609],"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":[0.0002556334,0.0007199052,0.149905,0.00009303766,0.002317302,0.00002324062,0.000730749,0.7218497,0.001986374,0.1185302,0.0001433357,0.003445578],"study_design_scores_gemma":[0.0002475183,0.00002920795,0.03312413,0.0000318063,0.000315454,8.630053e-7,0.00006112493,0.9634898,0.001732034,0.000809155,0.00001111578,0.0001478078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.690936,0.00003552316,0.3082021,0.00001665232,0.0003482243,0.0001762087,0.00004039521,0.00002507016,0.0002197951],"genre_scores_gemma":[0.9980605,0.00001177805,0.001761287,0.00002718754,0.00002260704,0.000001259986,0.00002004953,0.000005858505,0.00008944214],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3071245,"threshold_uncertainty_score":0.5884885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1042287017111895,"score_gpt":0.2376853763106874,"score_spread":0.1334566745994978,"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."}}