{"id":"W2211622316","doi":"10.1109/iccv.2015.289","title":"Contractive Rectifier Networks for Nonlinear Maximum Margin Classification","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"MNIST database; Margin (machine learning); Nonlinear system; Support vector machine; Rectifier (neural networks); Contraction (grammar); Computer science; Mathematical optimization; Mathematics; Algorithm; Control theory (sociology); Artificial intelligence; Machine learning; Artificial neural network; Recurrent neural network","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001951315,0.00100843,0.001057966,0.0005704255,0.0004266068,0.0009155313,0.001923035,0.001451436,0.003158428],"category_scores_gemma":[0.004440611,0.0005419853,0.0007909842,0.0008720218,0.001263888,0.003106977,0.001979784,0.002342991,0.001159796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007246345,"about_ca_system_score_gemma":0.0006996928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009463807,"about_ca_topic_score_gemma":0.001037085,"domain_scores_codex":[0.9992137,0.0002550922,0.0000654074,0.0002223929,0.0001824778,0.00006090155],"domain_scores_gemma":[0.9990113,0.0004690998,0.000140146,0.0001791594,0.0001627576,0.00003747517],"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":[0.0002300456,0.0001085681,0.0005762649,0.0001844953,0.00008154396,0.0001380878,0.0001724734,0.5457245,0.01671342,0.06587522,0.003278648,0.3669167],"study_design_scores_gemma":[0.00000711199,0.00003690822,0.00004527868,0.000008244642,0.000005773577,0.00002721338,0.00000685913,0.9817858,0.002319639,0.014859,0.0008911873,0.000006895098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009884704,0.0004957077,0.9871107,0.0001276884,0.00002796237,0.00003019344,0.00003256809,0.0002905521,0.001999932],"genre_scores_gemma":[0.5526857,0.001026191,0.4347948,0.0003700733,0.0001453928,0.0003074568,0.0004397777,0.0002350007,0.00999555],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003158428,"threshold_uncertainty_score":0.010566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05858663890322559,"score_gpt":0.2797400539479395,"score_spread":0.2211534150447139,"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."}}