{"id":"W1544532352","doi":"10.48550/arxiv.1301.3583","title":"Big Neural Networks Waste Capacity","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Leverage (statistics); Artificial neural network; Deep neural networks; Computer science; Parametrization (atmospheric modeling); Generalization; Gradient descent; Artificial intelligence; Generalization error; Mathematical optimization; Mathematics","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":[0.0001055439,0.0003360516,0.0003008014,0.0001166093,0.0002375309,0.000250654,0.00238569,0.0002880882,0.00002314448],"category_scores_gemma":[0.000005659799,0.0003582595,0.0002331995,0.0006276362,0.0001238956,0.0003023784,0.002398643,0.0008713651,0.00009437922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008873363,"about_ca_system_score_gemma":0.00004490742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002685181,"about_ca_topic_score_gemma":0.00004553248,"domain_scores_codex":[0.9980115,0.0001044928,0.0002003442,0.001127511,0.00007964131,0.0004764639],"domain_scores_gemma":[0.9976695,0.00008588981,0.0002366919,0.001625162,0.0001305161,0.0002522721],"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":[0.000002299081,0.00003950858,0.0003393569,0.00001272499,0.00002648703,0.00003515106,0.00002618985,0.8254883,0.00001187006,0.1689531,0.001781516,0.003283499],"study_design_scores_gemma":[0.0001453422,0.00001799669,0.0003588296,0.00002357096,0.00002434066,0.00000435103,0.000008318376,0.966005,0.00002456401,0.03233208,0.0006827649,0.0003728091],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3466974,0.00005037848,0.6500399,0.0002707065,0.0009404827,0.0003183266,0.000005607504,0.0002852481,0.001392002],"genre_scores_gemma":[0.9969081,0.0001243548,0.0008816651,0.0002971645,0.0004342203,0.000004209426,0.00001180677,0.00001802012,0.001320421],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6502108,"threshold_uncertainty_score":0.9998869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08645081458260345,"score_gpt":0.1739940902281608,"score_spread":0.08754327564555733,"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."}}