{"id":"W2099691301","doi":"10.1109/72.925559","title":"Thresholding neural network for adaptive noise reduction","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":159,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Thresholding; Artificial neural network; Artificial intelligence; Computer science; Adaptive filter; Noise (video); Noise reduction; Reduction (mathematics); Pattern recognition (psychology); Adaptive learning; Unsupervised learning; Algorithm; Mathematics; Image (mathematics)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000408711,0.0002892904,0.0002734741,0.0001301493,0.0007259906,0.0002334933,0.0005426364,0.0001529312,0.00001695453],"category_scores_gemma":[0.000004341255,0.0002778645,0.0002822119,0.0008224078,0.00006689432,0.0008092136,0.000004603951,0.0005163121,0.000007573328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006675545,"about_ca_system_score_gemma":0.00002102126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002278541,"about_ca_topic_score_gemma":0.000009206005,"domain_scores_codex":[0.9979135,0.0001979457,0.0003446282,0.0006078786,0.0002449631,0.0006910356],"domain_scores_gemma":[0.9987726,0.0003239448,0.0001101559,0.0005142897,0.000120125,0.0001588627],"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":[0.000267035,0.00005128812,0.000003373273,0.000002470957,0.00002170026,0.00001791637,0.00006499291,0.8075789,0.0004008661,0.0002734046,0.001112372,0.1902056],"study_design_scores_gemma":[0.0007499224,0.000399217,0.00005810079,0.00002817798,0.00003565091,0.0001870338,0.00001276827,0.9955711,0.00121427,0.0009717614,0.0004673991,0.0003046134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00794415,0.0001975725,0.9850358,0.0006366755,0.005137942,0.0004651925,0.000002933026,0.0003730534,0.0002066296],"genre_scores_gemma":[0.9440579,0.00006000552,0.05331128,0.0008030929,0.001020834,0.00009588536,0.000002167815,0.00003570792,0.0006131101],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9361138,"threshold_uncertainty_score":0.9999673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04049094824790187,"score_gpt":0.2826696035139611,"score_spread":0.2421786552660592,"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."}}