{"id":"W2581624817","doi":"10.48550/arxiv.1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":268,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Catastrophic Loss Reduction","keywords":"Computer science; Computation; Machine translation; Artificial neural network; Language model; Artificial intelligence; Layer (electronics); Translation (biology); Machine learning; Language translation; Algorithm","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008840928,0.001158138,0.0008974654,0.0002983584,0.0003880779,0.0007605561,0.002189534,0.001284696,0.00297331],"category_scores_gemma":[0.003333975,0.0007751594,0.0006815747,0.0004018593,0.001061397,0.002842216,0.002134648,0.002588248,0.001307234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007888452,"about_ca_system_score_gemma":0.001190627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00565509,"about_ca_topic_score_gemma":0.01177506,"domain_scores_codex":[0.9997111,0.00008883578,0.000009008164,0.00007935986,0.00006124593,0.0000503559],"domain_scores_gemma":[0.999368,0.0003025985,0.00004668953,0.0001566537,0.00007464062,0.00005136784],"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":[0.0005539732,0.0001731164,0.001256448,0.0001362893,0.0001923017,0.0002038347,0.0001837262,0.7311283,0.01919537,0.02993511,0.01207264,0.2049689],"study_design_scores_gemma":[0.00001128898,0.00002586,0.000076367,0.000005806718,0.00001232492,0.00001790961,0.000005404081,0.9878378,0.002542065,0.008551069,0.0009062695,0.000007884892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05896463,0.001116247,0.9297559,0.000946392,0.0001446652,0.00004858263,0.000228184,0.004778001,0.004017411],"genre_scores_gemma":[0.7184822,0.0006577988,0.268513,0.0008482662,0.0001465125,0.0001699323,0.001030676,0.0005690258,0.009582452],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00565509,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0848082490162567,"score_gpt":0.2135652458888167,"score_spread":0.12875699687256,"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."}}