{"id":"W2177899970","doi":"10.1609/aaai.v31i1.10777","title":"Denoising Criterion for Variational Auto-Encoding Framework","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":142,"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); Encoding (memory); Encoder; Artificial intelligence; Computer science; Algorithm; 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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006398885,0.0001869244,0.0002265039,0.00006876798,0.001168414,0.001138872,0.002522137,0.0001013238,0.00002966018],"category_scores_gemma":[0.002037972,0.0001449406,0.0001448091,0.0001440033,0.0002145857,0.0009336298,0.0004496164,0.0002013192,0.00001872959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003994668,"about_ca_system_score_gemma":0.00008584064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002673027,"about_ca_topic_score_gemma":0.000003848509,"domain_scores_codex":[0.9984725,0.0000145919,0.0003952846,0.0004572156,0.0003481465,0.0003122274],"domain_scores_gemma":[0.9979491,0.0002158769,0.0005772738,0.0004455684,0.0007447237,0.00006747194],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000305086,0.00004687389,0.00009903905,0.00001791399,0.00001467339,1.437382e-7,0.0005956834,0.0003686974,0.04318574,0.9098545,0.0001215749,0.04566469],"study_design_scores_gemma":[0.00001882022,0.00007788167,0.0005471616,0.000229043,0.00001069984,0.000001158613,0.00007238362,0.3288546,0.2781286,0.3917556,0.000148894,0.0001550522],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009427655,0.00001239501,0.9781022,0.007517604,0.0009364728,0.0003604758,0.000005539101,0.00004599231,0.003591669],"genre_scores_gemma":[0.9237328,0.00001198757,0.07561787,0.0001887926,0.0002938934,0.00002847463,2.747724e-7,0.000009928401,0.0001160217],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9143051,"threshold_uncertainty_score":0.999898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1027699205414761,"score_gpt":0.3279392752590403,"score_spread":0.2251693547175643,"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."}}