{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003514435,0.0008532359,0.00169132,0.001120021,0.0007262245,0.001144799,0.003181366,0.001386827,0.001668866],"category_scores_gemma":[0.005659227,0.0003919915,0.0006159369,0.001057394,0.001372954,0.001874318,0.001962808,0.001218707,0.0004567544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009114037,"about_ca_system_score_gemma":0.001095934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001658441,"about_ca_topic_score_gemma":0.001783523,"domain_scores_codex":[0.997912,0.0004382709,0.0001071978,0.0002458655,0.0010869,0.0002097385],"domain_scores_gemma":[0.9980301,0.0008339767,0.0002332479,0.0002283335,0.0005748145,0.00009963656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005127906,0.000362477,0.001973646,0.0001791775,0.0002544684,0.000147643,0.0001070283,0.3363762,0.01104004,0.02309169,0.003136639,0.6228183],"study_design_scores_gemma":[0.0000702008,0.0002393094,0.0002718165,0.000004385923,0.00002321038,0.0001181861,0.00001422298,0.9844505,0.006790742,0.00708131,0.0009138085,0.00002230825],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08384199,0.001010322,0.9080573,0.0004691946,0.0001412639,0.0002128868,0.0000422409,0.001068072,0.005156764],"genre_scores_gemma":[0.8532085,0.000300732,0.1423809,0.0003343062,0.00008387063,0.0001643323,0.00008305287,0.00006341015,0.003380712],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003514435,"threshold_uncertainty_score":0.01858634,"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."}}