{"id":"W2963501406","doi":"10.48550/arxiv.1511.06406","title":"Denoising Criterion for Variational Auto-Encoding Framework","year":2015,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Autoencoder; MNIST database; Noise reduction; Noise (video); Upper and lower bounds; Pattern recognition (psychology); Artificial intelligence; Computer science; Encoding (memory); Encoder; Algorithm; Noise measurement; Mathematics; 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":[0.0003154211,0.0001149974,0.0001234692,0.00008770442,0.0002149517,0.0001332268,0.0004881583,0.00007798694,0.00001046518],"category_scores_gemma":[0.000195388,0.0001266067,0.00007762887,0.000413943,0.00003371749,0.0008689475,0.0001591922,0.00008801265,0.00002942575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001116217,"about_ca_system_score_gemma":0.0001010951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000209022,"about_ca_topic_score_gemma":0.000003845806,"domain_scores_codex":[0.9990988,0.00007750662,0.0001042516,0.0004124289,0.00006875102,0.0002382886],"domain_scores_gemma":[0.9990558,0.0002198893,0.00007756989,0.0003001526,0.000205364,0.0001412439],"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":[0.00002800883,0.00003998474,0.0005961045,0.000005427963,0.00003047298,0.00002360783,0.0004353722,0.453678,0.0003924114,0.5424054,0.001133055,0.001232061],"study_design_scores_gemma":[0.0003053427,0.00005454672,0.0003545015,0.00001889162,0.00001529319,0.000002235157,0.00005848543,0.909854,0.0003832376,0.08641524,0.002375372,0.0001628453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01032666,0.00002591344,0.9878576,0.0002807446,0.0004845421,0.0001183075,0.000002791414,0.00009696122,0.000806427],"genre_scores_gemma":[0.9052469,0.000004566781,0.09401592,0.0001887729,0.00021074,5.926586e-7,0.000002570774,0.00000698246,0.0003229227],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8949203,"threshold_uncertainty_score":0.516287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1114331944100856,"score_gpt":0.2094352107019298,"score_spread":0.09800201629184423,"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."}}