{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006872791,0.001281618,0.001020543,0.0004278432,0.0004597799,0.0008741387,0.001539985,0.001100712,0.004272024],"category_scores_gemma":[0.002051158,0.0006309364,0.0006082397,0.0003866878,0.0009128868,0.001165224,0.001319689,0.001837661,0.0006022063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001681968,"about_ca_system_score_gemma":0.001663643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003965714,"about_ca_topic_score_gemma":0.006630536,"domain_scores_codex":[0.9995881,0.00007739258,0.00002176767,0.0001165858,0.0001098074,0.00008629519],"domain_scores_gemma":[0.9993076,0.0003368455,0.00008219122,0.00008369552,0.0001273909,0.00006230474],"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":[0.00003834054,0.0000308144,0.0003059205,0.00003940455,0.000009603353,0.00004504619,0.00002006223,0.9671409,0.00110663,0.004237083,0.001092872,0.02593328],"study_design_scores_gemma":[0.000006414138,0.00001909089,0.00002593636,0.000003396412,0.000002505064,0.000006737541,0.00000500961,0.9965703,0.0003948737,0.002624232,0.0003396135,0.000001846359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03126237,0.0004628556,0.9593983,0.0003858587,0.0001191792,0.0001066382,0.0001027928,0.001764924,0.006397128],"genre_scores_gemma":[0.782319,0.0002128619,0.2096366,0.000280001,0.00004930049,0.0002126425,0.0002158528,0.0002591815,0.006814552],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004272024,"threshold_uncertainty_score":0.01429129,"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."}}