{"id":"W4404313495","doi":"10.48550/arxiv.2410.19912","title":"Simmering: Sufficient is better than optimal for training neural networks","year":2024,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Universities Space Research Association","keywords":"Training (meteorology); Artificial neural network; Computer science; Deep neural networks; Training set; Artificial intelligence; Machine learning; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.007638019,0.001447818,0.001632208,0.001826059,0.001148062,0.002176953,0.002283561,0.002618009,0.01139924],"category_scores_gemma":[0.03334866,0.0009687689,0.001416227,0.001397407,0.002786829,0.006664675,0.00353984,0.004484934,0.002468342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001048458,"about_ca_system_score_gemma":0.002320588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001369338,"about_ca_topic_score_gemma":0.003318555,"domain_scores_codex":[0.9948558,0.002545698,0.0004275955,0.0009304313,0.0008789593,0.0003616084],"domain_scores_gemma":[0.9898816,0.006169855,0.0003733227,0.00238562,0.0009172258,0.000272303],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008857244,0.0002656789,0.00303094,0.0006412637,0.0002547786,0.0002087974,0.0004101516,0.1526525,0.007065352,0.55517,0.0312154,0.2481995],"study_design_scores_gemma":[0.00006722222,0.0001618143,0.0002919662,0.0001161516,0.00003186948,0.00009462149,0.00004289608,0.5136301,0.005700791,0.4707741,0.009057842,0.0000306991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01212547,0.0005905124,0.9749057,0.001525862,0.0002562845,0.00006080774,0.000327153,0.002467907,0.007740363],"genre_scores_gemma":[0.4096549,0.0006905834,0.5733463,0.002215713,0.0006749191,0.0005272101,0.001247899,0.002819675,0.008822804],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01139924,"threshold_uncertainty_score":0.04039419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07564053337504896,"score_gpt":0.2951807970211591,"score_spread":0.2195402636461101,"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."}}