{"id":"W2951470200","doi":"10.48550/arxiv.1311.1780","title":"Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal; Canadian Institute for Advanced Research","funders":"","keywords":"Pooling; Activation function; Computer science; Convolutional neural network; Perceptron; Artificial intelligence; Norm (philosophy); Artificial neural network; Benchmark (surveying); Unit sphere; Unit (ring theory); Pattern recognition (psychology); Deep learning; Algorithm; Mathematics; Combinatorics","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":[0.000304025,0.0003064184,0.0003166779,0.0002032603,0.0002893448,0.0003723361,0.0009941082,0.0002813846,0.00002275876],"category_scores_gemma":[0.00005583464,0.0003487479,0.0001688881,0.0002735377,0.00008586422,0.0004454301,0.001291096,0.0007447528,0.00002423918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001037485,"about_ca_system_score_gemma":0.000055079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005640357,"about_ca_topic_score_gemma":0.00002051515,"domain_scores_codex":[0.9981467,0.000116509,0.0002168299,0.0009877512,0.00007758188,0.0004546258],"domain_scores_gemma":[0.9985014,0.0002117627,0.0002752081,0.000608819,0.0001574154,0.0002453771],"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":[0.00002869696,0.00003047973,0.000654482,0.00006140327,0.00005701773,0.00002468963,0.0004316139,0.822624,0.000002351032,0.132972,0.0001929478,0.04292031],"study_design_scores_gemma":[0.0004914565,0.00006363247,0.0006536337,0.0000414541,0.00003816107,0.000004707807,0.0001373589,0.9837142,0.000001956115,0.012393,0.002077838,0.0003826047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04612101,0.0002625546,0.9506754,0.0002036312,0.0008941247,0.0004492375,0.000002651147,0.0002305788,0.001160832],"genre_scores_gemma":[0.9924465,0.0002825285,0.005914031,0.0002053972,0.0001441292,0.000003851806,0.00002477428,0.00002303051,0.0009557318],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9463255,"threshold_uncertainty_score":0.9998965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08332173844637374,"score_gpt":0.2046958372188885,"score_spread":0.1213740987725147,"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."}}