{"id":"W2115877322","doi":"10.1109/83.908518","title":"High-order image subsampling using feedforward artificial neural networks","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Feed forward; Artificial intelligence; Pattern recognition (psychology); Artificial neural network; Image (mathematics); Feedforward neural network; Process (computing); Image processing; Matching (statistics); Sequence (biology); Signal processing; Template matching; Algorithm; Computer vision; Mathematics; Digital signal processing","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":[0.0008116676,0.0005984945,0.0005304269,0.0004859093,0.0002671408,0.0004028397,0.0006834249,0.0005899461,0.001016069],"category_scores_gemma":[0.001175113,0.0002742867,0.0005159377,0.0003412897,0.0003772353,0.000705921,0.0003995217,0.0005751103,0.0002879993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004225787,"about_ca_system_score_gemma":0.0003585048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002173554,"about_ca_topic_score_gemma":0.004342941,"domain_scores_codex":[0.9997289,0.000060369,0.00001603749,0.00005807047,0.000112131,0.00002441057],"domain_scores_gemma":[0.9995835,0.0001598573,0.00004318632,0.00008476293,0.0001090966,0.00001953858],"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":[0.0003454087,0.0001274672,0.001247537,0.0001594839,0.00009031081,0.0001493023,0.0001577457,0.1744495,0.1491416,0.009286493,0.001661174,0.6631839],"study_design_scores_gemma":[0.00001224582,0.00007069335,0.0004129543,0.000007059495,0.00002107023,0.00007069388,0.000007142424,0.9637384,0.03133508,0.002363462,0.001947652,0.00001358015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01263663,0.0001522715,0.986131,0.00004498971,0.00002701279,0.00002278635,0.00001315878,0.0004276422,0.0005444597],"genre_scores_gemma":[0.2470209,0.0002127622,0.7501308,0.000101541,0.00006058393,0.00006502882,0.0000874216,0.00006447023,0.002256493],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002173554,"threshold_uncertainty_score":0.004321754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03743869459401864,"score_gpt":0.3039737190769058,"score_spread":0.2665350244828872,"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."}}