{"id":"W1593114658","doi":"10.48550/arxiv.1312.4314","title":"Learning Factored Representations in a Deep Mixture of Experts","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":137,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Parallelizable manifold; Computer science; Artificial intelligence; Layer (electronics); Class (philosophy); Machine learning; Deep learning; Space (punctuation); Algorithm","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":[0.00009688964,0.0001865111,0.0002680186,0.0003271474,0.0000757606,0.0000902355,0.001069595,0.0002068704,0.00003877952],"category_scores_gemma":[0.00008129789,0.0002094904,0.0001175251,0.0005934502,0.00006406643,0.000462604,0.001004521,0.0004475526,0.00001650435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000886124,"about_ca_system_score_gemma":0.0001253297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002845773,"about_ca_topic_score_gemma":0.00006517556,"domain_scores_codex":[0.9986582,0.0001103789,0.0001953105,0.0007032249,0.00008389787,0.0002489444],"domain_scores_gemma":[0.9987987,0.00008708351,0.0002735278,0.0006190072,0.0001316954,0.00008999735],"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":[0.00003740094,0.0003509262,0.1610221,0.0003708639,0.000156113,0.0006825674,0.01373159,0.7836535,0.006372743,0.01461906,0.0005045951,0.01849855],"study_design_scores_gemma":[0.001695872,0.0001290776,0.02958941,0.0007334128,0.00005822613,0.00001334394,0.002988125,0.8461757,0.03528305,0.08149463,0.000443326,0.001395789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6938456,0.0001018277,0.3037139,0.00006195863,0.0001604015,0.0001452468,0.000001017873,0.00009489921,0.001875119],"genre_scores_gemma":[0.9932358,0.00007422427,0.005799295,0.00002746891,0.00002497804,0.000001230878,0.000007417369,0.00000968309,0.0008199242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2993902,"threshold_uncertainty_score":0.854277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0519460007582218,"score_gpt":0.2001051598742186,"score_spread":0.1481591591159968,"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."}}