{"id":"W7133087281","doi":"","title":"Device Placement Optimization with Deep Reinforcement Learning","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"VLSI and FPGA Design Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Pipeline (software); Reinforcement learning; Deep learning; Artificial neural network; Deep neural networks; Generalizability theory; Scheduling (production processes); Granularity","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003146211,0.0007737984,0.0005743165,0.0004523596,0.000336605,0.0001975097,0.0002904214,0.0005127742,0.001422899],"category_scores_gemma":[0.00007014226,0.0008121944,0.0001205515,0.0008119208,0.00002673165,0.0001970414,0.0000481981,0.0008765805,0.0004721512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004487449,"about_ca_system_score_gemma":0.0001072022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002508044,"about_ca_topic_score_gemma":0.000141827,"domain_scores_codex":[0.9973388,0.00007601902,0.0006100716,0.0005954019,0.0006706766,0.0007090194],"domain_scores_gemma":[0.9986665,0.000131145,0.0003522225,0.0004251643,0.0002406054,0.0001844224],"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":[0.0001417048,0.00001978147,0.00004636793,0.0009531857,0.0002663038,0.00002134001,0.01137907,0.9841798,0.0008613002,0.0001178523,0.0004477673,0.001565533],"study_design_scores_gemma":[0.0007198339,0.000591292,0.00005597642,0.001404111,0.0003330619,0.000005601256,0.01321437,0.9723585,0.008973489,0.000008743607,0.001215161,0.001119871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003664847,0.0007063141,0.9528095,0.00008818496,0.0005577618,0.001624407,7.610391e-7,0.001919005,0.0386292],"genre_scores_gemma":[0.7285752,0.006567709,0.03212063,0.00007213746,0.0005156164,0.001281717,0.004653878,0.001088294,0.2251248],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9206889,"threshold_uncertainty_score":0.99949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01492511900388855,"score_gpt":0.2835500901668331,"score_spread":0.2686249711629445,"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."}}