{"id":"W2964226415","doi":"","title":"Deep Belief Networks for Image Denoising.","year":2013,"lang":"en","type":"article","venue":"","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Deep belief network; MNIST database; Artificial intelligence; Computer science; Pattern recognition (psychology); Additive white Gaussian noise; Noise reduction; Noise (video); Restricted Boltzmann machine; Deep learning; Feature extraction; Feature (linguistics); Image (mathematics); Artificial neural network; Gaussian noise; White noise","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":[0.001155487,0.001061267,0.001036211,0.0009182412,0.0002725199,0.001241942,0.001399934,0.001948997,0.003713741],"category_scores_gemma":[0.003349677,0.0007289394,0.0009103054,0.001244506,0.00083627,0.001656763,0.001189709,0.003178727,0.001385271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001268424,"about_ca_system_score_gemma":0.0007813001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003567774,"about_ca_topic_score_gemma":0.004749922,"domain_scores_codex":[0.9995227,0.0001463461,0.00003027974,0.00007660814,0.0001904404,0.00003375488],"domain_scores_gemma":[0.9991421,0.0004883088,0.0000928525,0.00009567396,0.000153112,0.00002794923],"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":[0.0001099525,0.00008093152,0.001022505,0.0008069677,0.0003027782,0.0001700681,0.00009991355,0.4925764,0.004409766,0.1568034,0.01578826,0.3278291],"study_design_scores_gemma":[0.00001048788,0.00002252012,0.000194997,0.00005422515,0.000023166,0.00004702674,0.00001255655,0.9180017,0.001590279,0.07113267,0.00889649,0.00001385737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00169797,0.005817504,0.9872311,0.0007673948,0.0001492269,0.00003583699,0.000225725,0.0006648704,0.003410299],"genre_scores_gemma":[0.2720557,0.01658153,0.6919101,0.0008873669,0.000580107,0.0004223989,0.001554219,0.0002989999,0.01570963],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003713741,"threshold_uncertainty_score":0.01242363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01448338351022658,"score_gpt":0.2650606834983171,"score_spread":0.2505772999880905,"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."}}