{"id":"W2110750681","doi":"","title":"Marginalized Denoising Auto-encoders for Nonlinear Representations","year":2014,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":111,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"","keywords":"Computer science; Speedup; Regularization (linguistics); Artificial intelligence; Noise reduction; Encoder; Representation (politics); Machine learning; Noise (video); Process (computing); Range (aeronautics); Training (meteorology); Algorithm; Pattern recognition (psychology); Engineering; Law; Parallel computing","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":[0.0002961106,0.00008609916,0.0001161802,0.00004837562,0.0002068863,0.0001842505,0.0003498132,0.00002902732,0.0000459461],"category_scores_gemma":[0.0001717663,0.00007347621,0.00008002556,0.0001649978,0.0000279724,0.0003737447,0.00007682792,0.00003657177,0.00002739582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001294954,"about_ca_system_score_gemma":0.00002820783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004036089,"about_ca_topic_score_gemma":0.00001795158,"domain_scores_codex":[0.9991768,0.00007068586,0.0001488714,0.0002890878,0.0001128699,0.0002017139],"domain_scores_gemma":[0.9991591,0.0002685607,0.00004923304,0.0003572585,0.0001034733,0.00006239864],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005621937,0.0002492194,0.0006801492,0.00004715185,0.0001801873,0.000004857003,0.001665046,0.06354173,0.02375101,0.3754151,0.1275084,0.4069009],"study_design_scores_gemma":[0.0003181987,0.00003403625,0.0001398749,0.000004474771,0.00000707867,0.000001526336,0.00002473015,0.9278017,0.005282504,0.004339231,0.0619388,0.0001078714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002174959,0.00001636044,0.9895923,0.002652133,0.000274333,0.0001610249,0.000001439627,0.0001134996,0.006971372],"genre_scores_gemma":[0.1057704,0.00000375944,0.8910873,0.00071187,0.0002281565,0.00003818162,0.000004640744,0.000007941273,0.002147721],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.86426,"threshold_uncertainty_score":0.2996273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.023164919105381,"score_gpt":0.2723559184844855,"score_spread":0.2491909993791045,"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."}}