{"id":"W2156366466","doi":"10.1109/mwscas.1994.518973","title":"Image compression using probabilistic winner-take-all learning","year":2002,"lang":"en","type":"article","venue":"","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Probabilistic logic; Computer science; Image compression; Data compression; Compression (physics); Artificial intelligence; Competitive learning; Image (mathematics); Algorithm; Machine learning; Artificial neural network; Image 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001667158,0.0001974213,0.0001989521,0.0001208856,0.0002177065,0.0001961313,0.001106745,0.00006850953,0.0003480823],"category_scores_gemma":[0.000158149,0.0001625804,0.00005567203,0.0003178577,0.00007019046,0.001412261,0.0008751726,0.0003043353,0.000134465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006080435,"about_ca_system_score_gemma":0.000009845382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001795632,"about_ca_topic_score_gemma":8.284578e-7,"domain_scores_codex":[0.9983031,0.0001288442,0.0003069805,0.0005520984,0.0003353212,0.0003736387],"domain_scores_gemma":[0.9986407,0.0001354916,0.0001462877,0.0008521141,0.00009471027,0.0001306523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001601295,0.0007682143,0.0004788102,0.0001588575,0.00004672535,0.0002188911,0.001391471,0.00813341,0.5957845,0.06123403,0.04997157,0.2817974],"study_design_scores_gemma":[0.0001722688,0.00005341251,0.000049439,0.0000817683,0.000003985596,0.00003677425,0.00001107481,0.9606717,0.01197289,0.004232513,0.02243968,0.0002745378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002698869,0.000118378,0.9865312,0.0002289626,0.0001214039,0.0002111541,0.000001263629,0.001551916,0.008536829],"genre_scores_gemma":[0.1243502,0.00002371192,0.8743545,0.0002609536,0.00004662729,0.00001322152,0.000004043824,0.00002004353,0.0009266149],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9525383,"threshold_uncertainty_score":0.6629838,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05536993154762849,"score_gpt":0.2969437980302834,"score_spread":0.2415738664826549,"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."}}