{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01101225,0.003232137,0.001586742,0.001986867,0.001202547,0.00434386,0.00428475,0.007656978,0.02303966],"category_scores_gemma":[0.1060701,0.001970702,0.0009111528,0.002170185,0.00314244,0.01130817,0.002761703,0.01567171,0.02142708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001596082,"about_ca_system_score_gemma":0.002271837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002233365,"about_ca_topic_score_gemma":0.004232524,"domain_scores_codex":[0.9907064,0.005234632,0.0007962825,0.0007807988,0.002244379,0.000237581],"domain_scores_gemma":[0.9697416,0.01767019,0.0009857827,0.003251689,0.00747682,0.0008739908],"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":[0.0002130757,0.0003020409,0.0006936055,0.001301692,0.00009768544,0.0002676399,0.0003746291,0.04188014,0.003699231,0.2206464,0.3637465,0.3667774],"study_design_scores_gemma":[0.0003448372,0.0002057815,0.000466285,0.002463101,0.00005791949,0.0004204924,0.0003014549,0.1240719,0.005607204,0.5165094,0.3493378,0.000213754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001242734,0.01412284,0.9188094,0.03897541,0.004976706,0.0002014889,0.000343975,0.004942434,0.01638503],"genre_scores_gemma":[0.02063367,0.01241045,0.9357203,0.008787625,0.002500548,0.0007816323,0.0005722755,0.003253388,0.01534024],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02303966,"threshold_uncertainty_score":0.07707536,"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."}}