{"id":"W2951650375","doi":"10.48550/arxiv.1206.5533","title":"Practical recommendations for gradient-based training of deep architectures","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":271,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Debugging; Artificial intelligence; Deep learning; Artificial neural network; Machine learning; Deep neural networks; Context (archaeology); Training (meteorology); Scale (ratio)","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":[0.0003346285,0.0002327799,0.0003013367,0.0004159581,0.0001198353,0.0000425948,0.0009232948,0.00020004,0.00002409459],"category_scores_gemma":[0.0002561188,0.0002706005,0.0002236594,0.0003983235,0.0001203096,0.0001542323,0.000488174,0.0003273503,0.000002737367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001118486,"about_ca_system_score_gemma":0.0002061397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001645229,"about_ca_topic_score_gemma":0.000009031143,"domain_scores_codex":[0.99858,0.0001141639,0.0002611148,0.0006232539,0.00008392167,0.0003374889],"domain_scores_gemma":[0.9977517,0.0006290104,0.000432877,0.0008027812,0.0002286888,0.0001549549],"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":[0.00003371569,0.0001991976,0.0001804383,0.00009231453,0.00007884589,0.000006090025,0.0009381456,0.2337192,0.0000156713,0.7610767,0.0004440619,0.003215592],"study_design_scores_gemma":[0.0003871574,0.00008379469,0.00007690728,0.00007093394,0.00008842834,0.000003710893,0.00007618962,0.9288651,0.0005108955,0.06923988,0.0003021808,0.0002947753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001815708,0.00001496172,0.9955443,0.0008042344,0.000478991,0.0005892825,0.00003345155,0.0002962251,0.0004228956],"genre_scores_gemma":[0.6022209,0.000003727624,0.3976063,0.00006345764,0.00002812081,0.000006737325,0.00003196294,0.00001213726,0.00002673642],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6951459,"threshold_uncertainty_score":0.9999746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1800527121404644,"score_gpt":0.2611330049116545,"score_spread":0.08108029277119005,"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."}}