{"id":"W2074130315","doi":"10.1142/s0218001403002411","title":"SCALING LARGE LEARNING PROBLEMS WITH HARD PARALLEL MIXTURES","year":2003,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; National Science Foundation","keywords":"Computer science; Generalization; Probabilistic logic; Parallelizable manifold; Support vector machine; Generative model; Machine learning; Upper and lower bounds; Artificial intelligence; Function (biology); Algorithm; Generative grammar; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003400097,0.0001000839,0.0001118569,0.0001119247,0.0001092622,0.000288383,0.0003179382,0.00003380223,0.00007183142],"category_scores_gemma":[0.00005962474,0.00007840805,0.00005342162,0.0001225282,0.00003817605,0.0003848024,0.00003664377,0.0002457939,0.00003157513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001489113,"about_ca_system_score_gemma":0.00002686688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005870173,"about_ca_topic_score_gemma":0.00001105707,"domain_scores_codex":[0.9989198,0.00007252156,0.0003808398,0.0001713883,0.000305644,0.0001498044],"domain_scores_gemma":[0.9990274,0.0001095022,0.0002909751,0.00006823937,0.0004177338,0.00008617342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002921396,0.0002095311,0.001876612,0.000008674287,0.00007948474,0.00006955105,0.0007732204,0.003860267,0.002034508,0.01361329,0.00006818461,0.9773775],"study_design_scores_gemma":[0.001453409,0.001754621,0.00331502,0.002169044,0.0001266583,0.004899277,0.002709957,0.2286676,0.1456488,0.5613028,0.04585899,0.002093853],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0998694,0.0001030504,0.8983513,0.001107037,0.0003002173,0.00006346598,0.000003253488,0.00001889604,0.0001833818],"genre_scores_gemma":[0.9875876,0.0002137494,0.01152745,0.0004539485,0.0001733601,0.000005577425,0.000003904645,0.000006583924,0.00002784843],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9752836,"threshold_uncertainty_score":0.3197387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06775681660741593,"score_gpt":0.2902994059329209,"score_spread":0.222542589325505,"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."}}