{"id":"W2963789586","doi":"","title":"Training deep neural networks via direct loss minimization","year":2016,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial neural network; Artificial intelligence; Minification; Machine learning; Deep neural networks; Entropy (arrow of time); Context (archaeology); Cross entropy; Ranking (information retrieval); Deep learning; Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002194125,0.001937092,0.0012824,0.0007156617,0.0004925386,0.001293435,0.001842335,0.001893045,0.002715179],"category_scores_gemma":[0.005388577,0.0008856594,0.000683122,0.0007585656,0.001108094,0.001868816,0.002229397,0.003212461,0.00141842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00165259,"about_ca_system_score_gemma":0.00179353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003008013,"about_ca_topic_score_gemma":0.006186543,"domain_scores_codex":[0.99902,0.0002655553,0.00005791491,0.0002225123,0.0003306932,0.0001033233],"domain_scores_gemma":[0.9985909,0.000687097,0.0001637481,0.0002009973,0.000289604,0.00006759174],"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":[0.00008397948,0.000144191,0.0006811268,0.0001227512,0.00007461337,0.00007472454,0.0000442383,0.7875523,0.005292933,0.01559246,0.004187136,0.1861496],"study_design_scores_gemma":[0.000007799464,0.00003660484,0.0000613658,0.000009214324,0.000004216618,0.00001667207,0.000004696505,0.9907089,0.001321925,0.007334057,0.0004900677,0.000004409291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01174898,0.0003028795,0.9839214,0.0002693075,0.0000415469,0.00008322692,0.00006748823,0.001156794,0.002408393],"genre_scores_gemma":[0.4291531,0.0005743766,0.556286,0.0006570305,0.0001295658,0.0007265375,0.0006621641,0.0005557145,0.01125558],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003008013,"threshold_uncertainty_score":0.01199037,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03707372032486093,"score_gpt":0.2969850488209083,"score_spread":0.2599113284960473,"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."}}