{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001145709,0.0001743709,0.0001328969,0.0001940953,0.000540847,0.00120212,0.0003001377,0.00006043655,0.000002191727],"category_scores_gemma":[0.00004519146,0.0001425298,0.00001278038,0.0008094755,0.0001148333,0.006662145,0.00009885753,0.0000868075,0.0000180928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008660879,"about_ca_system_score_gemma":0.0001268347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001825334,"about_ca_topic_score_gemma":0.000001943417,"domain_scores_codex":[0.9986688,0.00003524629,0.000453728,0.0002376156,0.0003367742,0.0002677693],"domain_scores_gemma":[0.9983426,0.00002647883,0.0004562937,0.0002637708,0.0008116128,0.000099187],"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":[0.00009969536,0.00003578961,0.001170008,0.0003171877,0.00001177886,8.141096e-7,0.003002318,0.9397981,0.0002758129,0.01501077,0.000174973,0.04010275],"study_design_scores_gemma":[0.0004620073,0.000187003,0.0005106956,0.00006063377,0.000004525751,0.00008700613,0.00009718146,0.9959209,0.0004955976,0.0000236395,0.001970505,0.0001803285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0174106,0.00005609947,0.9797602,0.0009913323,0.0001256037,0.0006626521,0.000004914085,0.0003363274,0.0006522674],"genre_scores_gemma":[0.9520732,0.000006746629,0.04652411,0.0008500677,0.0002386355,0.0001289471,0.00004848799,0.0000119076,0.0001178517],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9346626,"threshold_uncertainty_score":0.9998347,"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."}}