{"id":"W1507070875","doi":"10.48550/arxiv.1206.4635","title":"Deep Mixtures of Factor Analysers","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Overfitting; Latent variable; Computer science; Layer (electronics); Factor (programming language); Graphical model; Artificial intelligence; Boltzmann machine; Machine learning; Deep learning; Variety (cybernetics); Restricted Boltzmann machine; Inference; Artificial neural network; Chemistry","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":[0.00006235304,0.0001005782,0.0001296552,0.0001174335,0.00005966202,0.00002301745,0.0007247974,0.00005359266,0.000073387],"category_scores_gemma":[0.00001594818,0.00009604097,0.00007772748,0.0006868489,0.00005758625,0.0007664482,0.0001509727,0.00007582777,0.00004706413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000024658,"about_ca_system_score_gemma":0.00003330017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002847877,"about_ca_topic_score_gemma":0.000007187663,"domain_scores_codex":[0.9993266,0.0000304884,0.00009533005,0.0002289154,0.0000561059,0.0002625634],"domain_scores_gemma":[0.9992666,0.00003870052,0.00009880127,0.0003887731,0.00006472097,0.0001424525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001363373,0.0001621049,0.1307539,0.0000518785,0.00007277114,0.00002994831,0.0008764687,0.002182323,0.001043871,0.8609852,0.0001541575,0.00367377],"study_design_scores_gemma":[0.001833838,0.0003769778,0.3133784,0.00009778504,0.0001846798,0.00003423624,0.0006667924,0.5680045,0.03696165,0.07386481,0.002863313,0.001733007],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2199792,0.00007961726,0.7767637,0.0000317734,0.0001053435,0.00003471131,0.000001283217,0.00004949722,0.002954889],"genre_scores_gemma":[0.9970528,0.00002376156,0.002600007,0.00005142585,0.00002334954,7.983431e-8,5.935749e-7,0.000003688094,0.0002442555],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7871204,"threshold_uncertainty_score":0.3916437,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04871719549440465,"score_gpt":0.1822482766019795,"score_spread":0.1335310811075748,"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."}}