{"id":"W2980583983","doi":"10.48550/arxiv.1910.06548","title":"Training CNNs faster with Dynamic Input and Kernel Downsampling","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Upsampling; Computer science; Hyperparameter; Pooling; Residual; Convolution (computer science); Kernel (algebra); Reduction (mathematics); Algorithm; Backpropagation; Filter (signal processing); Generalization; Feature (linguistics); Key (lock); Convolutional neural network; Artificial intelligence; Pattern recognition (psychology); Mathematics; Artificial neural network; Computer vision","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":[0.00009219773,0.0003172349,0.0003100828,0.0001684964,0.0001597982,0.0001255712,0.001158782,0.0001724687,0.000005154627],"category_scores_gemma":[0.000006613962,0.000328234,0.00007042038,0.0004524981,0.0001253489,0.0004172632,0.001593287,0.000606096,0.00004283161],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001178253,"about_ca_system_score_gemma":0.0001147553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001484752,"about_ca_topic_score_gemma":0.0000396318,"domain_scores_codex":[0.9980585,0.00004593737,0.0001531372,0.001286446,0.00008034967,0.0003756048],"domain_scores_gemma":[0.9981955,0.0001485436,0.0002285971,0.001197897,0.00007996499,0.0001494406],"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":[0.00002165437,0.0000291765,0.001796159,0.00005900485,0.00006587827,0.00008125407,0.0007006685,0.9308987,0.00008211785,0.06040237,0.00001660249,0.005846376],"study_design_scores_gemma":[0.0004176789,0.000049703,0.00199595,0.0001339556,0.00004261412,0.00002290132,0.0001132861,0.9708018,0.00001642652,0.02534068,0.0005381326,0.0005269056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2215261,0.00004137457,0.7765291,0.0001147604,0.0001253819,0.0003280669,0.000007854471,0.0002037411,0.001123591],"genre_scores_gemma":[0.9808815,0.0001162379,0.01768696,0.0001453722,0.00003265076,0.000002517882,0.00001232497,0.00002549058,0.001096986],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7593554,"threshold_uncertainty_score":0.999917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07569608199522461,"score_gpt":0.2062172710992033,"score_spread":0.1305211891039787,"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."}}