{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001200311,0.00119202,0.0008338741,0.0006713258,0.0002956083,0.0009000195,0.001174027,0.001380799,0.002508595],"category_scores_gemma":[0.003162945,0.000786704,0.001212076,0.0005757764,0.0008583512,0.002901652,0.001483787,0.001975943,0.0008515993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008911255,"about_ca_system_score_gemma":0.0006986987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005523539,"about_ca_topic_score_gemma":0.0070478,"domain_scores_codex":[0.9994835,0.0001652731,0.0000176278,0.0001823896,0.00007084769,0.00008031349],"domain_scores_gemma":[0.9992937,0.0003441799,0.00006227405,0.0001147272,0.0001253382,0.00005981035],"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":[0.0003524787,0.00009916011,0.00222446,0.00007992915,0.0001582129,0.0001350646,0.0002317037,0.791155,0.01179631,0.02936769,0.004285135,0.1601148],"study_design_scores_gemma":[0.000007179409,0.0000182805,0.00008353345,0.000005280821,0.000008247758,0.00001901417,0.000008851398,0.9884536,0.001130352,0.009853871,0.0004064266,0.000005440777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04218943,0.000320305,0.954144,0.0003258603,0.00004300142,0.00002662673,0.0001493428,0.001142515,0.001658896],"genre_scores_gemma":[0.7320677,0.0002999336,0.2598183,0.000361819,0.00007874097,0.00008717394,0.000553177,0.0001755536,0.006557639],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005523539,"threshold_uncertainty_score":0.01098275,"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."}}