{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001551179,0.0002041561,0.0001632598,0.0001390048,0.0001988178,0.0001450666,0.0009883615,0.00006314666,0.0002098397],"category_scores_gemma":[0.000154109,0.000157545,0.00006933644,0.0002541315,0.00006227908,0.0005817963,0.0002017684,0.0003110419,0.00007638281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007709866,"about_ca_system_score_gemma":0.0000183462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000860107,"about_ca_topic_score_gemma":0.00001740305,"domain_scores_codex":[0.9983779,0.0001277522,0.0002894163,0.0005350242,0.000356534,0.0003133786],"domain_scores_gemma":[0.9988525,0.0003448645,0.0002197507,0.0003011528,0.0001755429,0.0001062269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002658596,0.00002946885,0.002456548,0.000001127247,0.00002276085,0.0000153562,0.0001926615,0.1559985,0.001042656,0.1127259,0.00002270865,0.7274657],"study_design_scores_gemma":[0.0003199411,0.00007013627,0.001013305,0.00002947662,0.000002927914,0.00002550375,0.00000739254,0.9906861,0.0001166467,0.004046128,0.003472648,0.0002097957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00199572,0.00003178687,0.9793006,0.006293365,0.0004990451,0.0001188862,0.000002585572,0.0003631872,0.01139481],"genre_scores_gemma":[0.9897085,0.00006377894,0.008593721,0.0004794838,0.0002559817,0.00004166,0.00002310773,0.00002081869,0.0008129415],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9877128,"threshold_uncertainty_score":0.6424497,"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."}}