Designing Effective Sparse Expert Models. Zoph, B., Bello, I., Kumar, S., Du, N., Huang, Y., Dean, J., Shazeer, N., & Fedus, W. CoRR, 2022.
Designing Effective Sparse Expert Models [link]Paper  bibtex   
@article{DBLP:journals/corr/abs-2202-08906,
  author       = {Barret Zoph and
                  Irwan Bello and
                  Sameer Kumar and
                  Nan Du and
                  Yanping Huang and
                  Jeff Dean and
                  Noam Shazeer and
                  William Fedus},
  title        = {Designing Effective Sparse Expert Models},
  journal      = {CoRR},
  volume       = {abs/2202.08906},
  year         = {2022},
  url          = {https://arxiv.org/abs/2202.08906},
  eprinttype    = {arXiv},
  eprint       = {2202.08906},
  timestamp    = {Thu, 17 Aug 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2202-08906.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

Downloads: 0