{"id":"W4312709677","doi":"10.1109/cvpr52688.2022.01005","title":"Exploiting Explainable Metrics for Augmented SGD","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of New Brunswick","funders":"","keywords":"Computer science; Stochastic gradient descent; Generalization; Exploit; Artificial intelligence; Machine learning; Overhead (engineering); Deep learning; Learning to rank; Artificial neural network; Measure (data warehouse); Rank (graph theory); Layer (electronics); Deep neural networks; Network architecture; Data mining; Ranking (information retrieval); Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004316493,0.0003159827,0.0003368253,0.000390825,0.00106033,0.0003614538,0.0007419902,0.00006183607,0.0002933588],"category_scores_gemma":[0.00001947406,0.0003294998,0.0001186203,0.0008286324,0.00004204933,0.0005503198,0.0005833844,0.000407686,0.00006702144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009844797,"about_ca_system_score_gemma":0.00004777456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008870848,"about_ca_topic_score_gemma":0.000004308116,"domain_scores_codex":[0.9973056,0.0002246445,0.0004767408,0.0009838148,0.0005207269,0.0004884206],"domain_scores_gemma":[0.9982078,0.000526542,0.0002984195,0.0005302544,0.0002354799,0.0002014822],"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":[0.00004118644,0.0002275058,0.00006208444,0.00003756121,0.00002132822,0.00001867908,0.0002782129,0.0005979648,0.0009670238,0.002414447,0.009816179,0.9855178],"study_design_scores_gemma":[0.001781098,0.00151747,0.0002158168,0.0001006207,0.00001977992,0.00008154666,0.0002133478,0.9536358,0.002188134,0.01429314,0.0252214,0.0007318366],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0285394,0.00004575949,0.9665362,0.002076195,0.001036833,0.0008840027,0.0001137072,0.0003144054,0.0004534674],"genre_scores_gemma":[0.9428504,0.0001925191,0.04723372,0.006981296,0.0003845028,0.001507444,0.0003411709,0.00005457617,0.0004544504],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.984786,"threshold_uncertainty_score":0.9999157,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07788462505945132,"score_gpt":0.3020840148417718,"score_spread":0.2241993897823205,"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."}}