{"id":"W3006210322","doi":"","title":"Cutting out the Middle-Man: Training and Evaluating Energy-Based Models without Sampling","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Artificial neural network; Function (biology); Sampling (signal processing); Training set; Goodness of fit; Energy (signal processing); Artificial intelligence; Feature (linguistics); Algorithm; Machine learning; Pattern recognition (psychology); Mathematics; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.000356027,0.0001784532,0.0001935848,0.00004617302,0.0004777045,0.0001689085,0.0006102414,0.0000501023,0.000006650017],"category_scores_gemma":[0.00008469417,0.000155149,0.00008346973,0.0003829132,0.00008968493,0.0005946287,0.0002619587,0.0001511314,0.000004911258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002843397,"about_ca_system_score_gemma":0.00008624597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003425749,"about_ca_topic_score_gemma":0.00001271051,"domain_scores_codex":[0.9986458,0.0001991712,0.0001456027,0.0006013286,0.0001009242,0.0003071368],"domain_scores_gemma":[0.9990478,0.00027394,0.0001251145,0.0003133514,0.00008867978,0.0001511171],"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":[0.00001318819,0.000008317955,0.0002203454,0.00000691677,0.00002801726,0.00001343563,0.003149555,0.9650192,0.0004712784,0.02210812,0.00001952758,0.008942145],"study_design_scores_gemma":[0.0003787724,0.00006449944,0.00002673706,0.00003154882,0.0000332959,0.000001129548,0.0005837666,0.9940286,0.0003709203,0.003992087,0.0002966965,0.0001919173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04306104,0.00007225429,0.9548867,0.0007886998,0.00009004944,0.00008707293,0.000001353129,0.0001048861,0.0009079747],"genre_scores_gemma":[0.9717223,0.00001183289,0.02661401,0.001423035,0.0001302504,6.300631e-7,0.000001133766,0.00001224334,0.00008457748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9286612,"threshold_uncertainty_score":0.6326792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3545926430824564,"score_gpt":0.2258246029983128,"score_spread":0.1287680400841436,"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."}}