{"id":"W2962971773","doi":"10.1109/cvpr.2017.668","title":"Deep Pyramidal Residual Networks","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":687,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Residual; Convolutional neural network; Upsampling; Computer science; Benchmark (surveying); Artificial intelligence; Feature (linguistics); Deep learning; Dimension (graph theory); Pattern recognition (psychology); Generalization; Residual neural network; Pooling; Artificial neural network; Network architecture; Image (mathematics); Algorithm; Mathematics; Cartography","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":[0.00046319,0.0007994846,0.0006754704,0.000393657,0.0002351345,0.0006528395,0.00143082,0.0007592823,0.00402526],"category_scores_gemma":[0.001564654,0.0002776876,0.0005417766,0.0005676848,0.0004923801,0.001320431,0.001010025,0.001158086,0.001722958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000608534,"about_ca_system_score_gemma":0.0008024987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003982062,"about_ca_topic_score_gemma":0.005708846,"domain_scores_codex":[0.9996736,0.00003599555,0.00001873611,0.0001067159,0.0001005244,0.00006440886],"domain_scores_gemma":[0.9996542,0.00006733509,0.00004953212,0.00008873487,0.000110865,0.0000293875],"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":[0.0002904403,0.000108842,0.001258287,0.00029228,0.0001530405,0.0001697949,0.00006330718,0.4442671,0.03220294,0.0454062,0.01641438,0.4593734],"study_design_scores_gemma":[0.00001970778,0.00008189983,0.0003330316,0.00001676636,0.00002720294,0.00007141367,0.000009528044,0.9724874,0.008018194,0.01334682,0.005575629,0.00001239734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03649091,0.002003767,0.9451591,0.0004744658,0.000172039,0.00006811055,0.0006514671,0.003780509,0.01119966],"genre_scores_gemma":[0.6807754,0.002057704,0.2926307,0.0004930483,0.0001755976,0.0001351533,0.002956561,0.0003081386,0.02046775],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00402526,"threshold_uncertainty_score":0.01346582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03010212868599168,"score_gpt":0.2971226287962158,"score_spread":0.2670205001102242,"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."}}