A noisy top-k gated mixture-of-experts layer between LSTMs scales neural networks to 137B parameters with sub-linear compute, beating SOTA on language modeling and machine translation.
Low-rank approximations for conditional feedforward computation in deep neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2017 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
A noisy top-k gated mixture-of-experts layer between LSTMs scales neural networks to 137B parameters with sub-linear compute, beating SOTA on language modeling and machine translation.