{"id":"W2191540403","doi":"","title":"On Autoencoders and Score Matching for Energy Based Models","year":2011,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of British Columbia","funders":"","keywords":"Autoencoder; Artificial intelligence; Pattern recognition (psychology); Matching (statistics); Gaussian; Estimator; Regularization (linguistics); Computer science; Feature extraction; Mathematics; Statistics; Deep learning","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":[0.0001044373,0.00008863244,0.00008810615,0.00004455567,0.0001038763,0.00006049616,0.0002098397,0.00002796213,0.00001977462],"category_scores_gemma":[0.000007604722,0.00006908768,0.00003794676,0.00005914634,0.0000202947,0.0003223357,0.00004765071,0.00002453821,0.000001350947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007507573,"about_ca_system_score_gemma":0.00002195232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001522239,"about_ca_topic_score_gemma":0.00002761938,"domain_scores_codex":[0.9994114,0.00002496877,0.00008445348,0.0002488698,0.00007243948,0.0001578755],"domain_scores_gemma":[0.9995915,0.0000945012,0.00002715027,0.0001978416,0.00003149252,0.00005757009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002171568,0.00004588054,0.000008867365,0.000005618494,0.00001468299,0.000002168935,0.000482953,0.08534435,0.000265603,0.8779348,0.001929845,0.0339435],"study_design_scores_gemma":[0.0001574979,0.00007361668,0.00003650327,0.000007644366,0.000002451857,3.987674e-7,0.0000101724,0.8543082,0.003437805,0.1417665,0.0001127565,0.0000863349],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005444507,0.00001780733,0.9890205,0.0002070507,0.0001163996,0.0000634273,9.571557e-7,0.00006224142,0.009967172],"genre_scores_gemma":[0.6246624,0.000002197502,0.3740901,0.001056518,0.00001851375,0.00001121092,4.619659e-7,0.000004480503,0.0001541194],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7689639,"threshold_uncertainty_score":0.2817314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05270944082733099,"score_gpt":0.2123231543900584,"score_spread":0.1596137135627274,"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."}}