{"id":"W2279398222","doi":"10.1109/cvprw.2016.141","title":"Efficient Deep Feature Learning and Extraction via StochasticNets","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Nvidia","keywords":"Computer science; Artificial intelligence; Deep learning; Convolutional neural network; Feature extraction; Feature (linguistics); Deep neural networks; Artificial neural network; Pattern recognition (psychology); Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000623377,0.0008528564,0.0008320509,0.0007556158,0.0002765573,0.00085971,0.0007544028,0.0005808433,0.001708388],"category_scores_gemma":[0.002272552,0.0005808715,0.0009139133,0.0008673118,0.0004740768,0.002072608,0.001076937,0.001048556,0.0008193241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005538358,"about_ca_system_score_gemma":0.0006230281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001727233,"about_ca_topic_score_gemma":0.002531652,"domain_scores_codex":[0.9996496,0.00006247764,0.0000337669,0.0000813207,0.0001295722,0.00004325966],"domain_scores_gemma":[0.9994506,0.0002203381,0.00008706428,0.0001142947,0.0001052422,0.00002242252],"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":[0.0001698803,0.00006220394,0.001585235,0.0001883013,0.00008443728,0.0002372544,0.0000739864,0.4524978,0.03666466,0.03706695,0.004660047,0.4667093],"study_design_scores_gemma":[0.000004958462,0.00001991742,0.0002409069,0.000006037777,0.000007377343,0.00005343645,0.000006707628,0.9777285,0.006376626,0.01414855,0.001399606,0.000007279534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00827706,0.0001141511,0.9901621,0.00008818381,0.00001549082,0.00001940288,0.0001147455,0.0007552734,0.0004535534],"genre_scores_gemma":[0.4458306,0.0004633267,0.548433,0.0001382743,0.0000528657,0.0001432183,0.001395435,0.0002103931,0.003332874],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001727233,"threshold_uncertainty_score":0.005715132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01123483696721018,"score_gpt":0.2799591947123151,"score_spread":0.2687243577451049,"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."}}