{"id":"W2531425418","doi":"10.48550/arxiv.1610.02915","title":"Deep Pyramidal Residual Networks","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science, ICT and Future Planning","keywords":"Residual; Computer science; Upsampling; Convolutional neural network; Benchmark (surveying); Feature (linguistics); Artificial intelligence; Code (set theory); Deep learning; Dimension (graph theory); Generalization; Pooling; Residual neural network; Pattern recognition (psychology); Network architecture; Artificial neural network; Image (mathematics); Algorithm; Cartography; Mathematics; Geography; Set (abstract data type)","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":[0.0001296543,0.0003639188,0.0003070081,0.0001577481,0.0002391373,0.0001030585,0.002979964,0.0003507562,0.00002496294],"category_scores_gemma":[0.00001927074,0.0003715451,0.0001736667,0.0006043332,0.0001931849,0.000426679,0.003544923,0.000677906,0.0001855366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002141244,"about_ca_system_score_gemma":0.000102204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000112731,"about_ca_topic_score_gemma":0.00002892088,"domain_scores_codex":[0.9975511,0.0001133973,0.0002242847,0.00146181,0.0000940508,0.0005553489],"domain_scores_gemma":[0.9969853,0.0002188255,0.0002899565,0.002128299,0.0001393958,0.0002382534],"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":[0.0000105118,0.00002839493,0.0003576566,0.000007339239,0.00002987273,0.0001066973,0.00002181594,0.5812041,0.00001089118,0.4147688,0.000751358,0.002702554],"study_design_scores_gemma":[0.0002666446,0.00001999676,0.00063661,0.0000445869,0.00002616497,0.00000601194,0.000005273962,0.7661918,0.00004251204,0.2310151,0.00128243,0.000462902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006612959,0.0001225368,0.9875795,0.0004640183,0.0006097908,0.0003447954,0.00000623335,0.0006103287,0.003649895],"genre_scores_gemma":[0.9918732,0.0002783169,0.005197174,0.0002099018,0.0004128536,0.000003990763,0.00001291804,0.00002975381,0.001981879],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9852602,"threshold_uncertainty_score":0.9998736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05151344467729533,"score_gpt":0.1939313041761768,"score_spread":0.1424178594988814,"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."}}