@ARTICLE{outrageously_large_neural_nets,
     author = {Shazeer, N. and Mirhoseini, A. and Maziarz, K. and Davis, A. and Le, Q. and Hinton, G. and Dean, J.},
    journal={ArXiv preprint},
    title={Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer},
       year = 2017,
      month = jan,
     url = {https://arxiv.org/abs/1701.06538},
  }

{"_id":"CKmFTepme4QhHuHt8","bibbaseid":"shazeer-mirhoseini-maziarz-davis-le-hinton-dean-outrageouslylargeneuralnetworksthesparselygatedmixtureofexpertslayer-2017","author_short":["Shazeer, N.","Mirhoseini, A.","Maziarz, K.","Davis, A.","Le, Q.","Hinton, G.","Dean, J."],"bibdata":{"bibtype":"article","type":"article","author":[{"propositions":[],"lastnames":["Shazeer"],"firstnames":["N."],"suffixes":[]},{"propositions":[],"lastnames":["Mirhoseini"],"firstnames":["A."],"suffixes":[]},{"propositions":[],"lastnames":["Maziarz"],"firstnames":["K."],"suffixes":[]},{"propositions":[],"lastnames":["Davis"],"firstnames":["A."],"suffixes":[]},{"propositions":[],"lastnames":["Le"],"firstnames":["Q."],"suffixes":[]},{"propositions":[],"lastnames":["Hinton"],"firstnames":["G."],"suffixes":[]},{"propositions":[],"lastnames":["Dean"],"firstnames":["J."],"suffixes":[]}],"journal":"ArXiv preprint","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","year":"2017","month":"January","url":"https://arxiv.org/abs/1701.06538","bibtex":"@ARTICLE{outrageously_large_neural_nets,\n author = {Shazeer, N. and Mirhoseini, A. and Maziarz, K. and Davis, A. and Le, Q. and Hinton, G. and Dean, J.},\n journal={ArXiv preprint},\n title={Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer},\n year = 2017,\n month = jan,\n url = {https://arxiv.org/abs/1701.06538},\n }\n ","author_short":["Shazeer, N.","Mirhoseini, A.","Maziarz, K.","Davis, A.","Le, Q.","Hinton, G.","Dean, J."],"key":"outrageously_large_neural_nets","id":"outrageously_large_neural_nets","bibbaseid":"shazeer-mirhoseini-maziarz-davis-le-hinton-dean-outrageouslylargeneuralnetworksthesparselygatedmixtureofexpertslayer-2017","role":"author","urls":{"Paper":"https://arxiv.org/abs/1701.06538"},"metadata":{"authorlinks":{}},"downloads":2,"html":""},"bibtype":"article","biburl":"https://worldmodels.github.io/","dataSources":["h7kKWXpJh2iaX92T5","cx4WvnDhXJhiLqdQo","D5E4ufAwssrYkjTMx"],"keywords":[],"search_terms":["outrageously","large","neural","networks","sparsely","gated","mixture","experts","layer","shazeer","mirhoseini","maziarz","davis","le","hinton","dean"],"title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","year":2017,"downloads":2}