{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00100894,0.001889579,0.001210131,0.0007159499,0.0003536585,0.001490856,0.001921808,0.001009772,0.009269213],"category_scores_gemma":[0.004952921,0.0008914953,0.001216223,0.0007334677,0.0004679768,0.003582961,0.00148042,0.002542526,0.005064744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001361798,"about_ca_system_score_gemma":0.001272769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01056852,"about_ca_topic_score_gemma":0.01797384,"domain_scores_codex":[0.9989896,0.00009249721,0.00006476848,0.0003519177,0.0003325436,0.0001686008],"domain_scores_gemma":[0.9985025,0.0003384353,0.0001103644,0.0006113711,0.0003858046,0.00005158421],"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":[0.0004549979,0.0003178185,0.00239081,0.0002789486,0.0002977664,0.0002391491,0.0001914259,0.3439985,0.0819976,0.01290172,0.02504133,0.53189],"study_design_scores_gemma":[0.00004600602,0.0000715761,0.001002023,0.00003283625,0.00005147101,0.00008762323,0.00003439831,0.9470944,0.03424816,0.008086572,0.009219401,0.00002560289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1289036,0.001001757,0.8211341,0.001106101,0.0006605401,0.0001954381,0.001008266,0.03109057,0.01489974],"genre_scores_gemma":[0.4995997,0.0006568995,0.4709379,0.000891308,0.0001933953,0.000354645,0.00432501,0.002780824,0.02026036],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01056852,"threshold_uncertainty_score":0.0310086,"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."}}