{"id":"W2890720247","doi":"","title":"Post: Device Placement with Cross-Entropy Minimization and Proximal Policy Optimization","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Cross entropy; Minification; Reinforcement learning; Computation; Artificial neural network; Cross-entropy method; Entropy (arrow of time); Importance sampling; Deep neural networks; Machine learning; Monte Carlo method; Empirical risk minimization; Artificial intelligence; Mathematical optimization; Principle of maximum entropy; Algorithm; Optimization problem; Mathematics","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":[0.001464261,0.001280417,0.001366367,0.0004965428,0.0005463249,0.001171643,0.0020398,0.001995938,0.004711889],"category_scores_gemma":[0.004678664,0.0007671538,0.0006442207,0.0004904568,0.001192733,0.001553519,0.001962173,0.002032435,0.001076977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00124837,"about_ca_system_score_gemma":0.002207661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003509899,"about_ca_topic_score_gemma":0.00387434,"domain_scores_codex":[0.9992536,0.0002267242,0.00003585814,0.0001558302,0.0002105246,0.0001174781],"domain_scores_gemma":[0.9985813,0.0007547757,0.0001347408,0.0002078863,0.0002225444,0.00009876958],"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":[0.000126884,0.00008666507,0.0004950333,0.00005551168,0.00002940565,0.00006078825,0.00003868055,0.9211771,0.00143264,0.008319715,0.002830951,0.0653467],"study_design_scores_gemma":[0.000009869244,0.00002729355,0.00003393836,0.000003772896,0.00000297436,0.00001049322,0.000004178135,0.9963745,0.0006063816,0.002604753,0.0003188507,0.000002856532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01409231,0.0001823675,0.9814275,0.0002381906,0.00008226638,0.00006881275,0.00003872678,0.001512317,0.002357552],"genre_scores_gemma":[0.5925046,0.0001523806,0.39843,0.0003775702,0.0001046811,0.0003391393,0.0002004105,0.0005238329,0.007367427],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004711889,"threshold_uncertainty_score":0.01576287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01255468471138568,"score_gpt":0.2784801996469697,"score_spread":0.2659255149355841,"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."}}