{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007175889,0.001951295,0.001894675,0.001469186,0.0006489188,0.001652162,0.003225994,0.002741213,0.00255252],"category_scores_gemma":[0.01959041,0.001336473,0.001216844,0.0008912515,0.002583123,0.003175456,0.003409268,0.003333035,0.0007798073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001910139,"about_ca_system_score_gemma":0.001467684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00582916,"about_ca_topic_score_gemma":0.00629229,"domain_scores_codex":[0.9978818,0.001030804,0.0001025911,0.0003860273,0.0004645852,0.0001342673],"domain_scores_gemma":[0.9931792,0.00480958,0.000396049,0.0009424593,0.0004547597,0.0002179733],"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":[0.0001171429,0.00005935045,0.0009804755,0.00004805338,0.00006939923,0.00003780248,0.00004365573,0.9418982,0.001223393,0.008314687,0.0007211792,0.04648671],"study_design_scores_gemma":[0.000003611935,0.00001879262,0.00003666543,0.000004814093,0.000003387861,0.000007577056,0.000002549089,0.9962254,0.0004515196,0.003140803,0.0001014104,0.000003524048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02314128,0.0003477053,0.9740675,0.0002487951,0.00005202829,0.00006012064,0.00006385305,0.0009055716,0.001113057],"genre_scores_gemma":[0.6363487,0.0003302805,0.3585138,0.0005089077,0.00009604352,0.0002881167,0.0005231923,0.0005778367,0.002813053],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007175889,"threshold_uncertainty_score":0.03795022,"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."}}