-
Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout
The vast majority of deep models use multiple gradient signals, typicall...
10/14/2020 ∙ by Zhao Chen, et al. ∙
0
∙
share
read it
-
GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
Neural network scaling has been critical for improving the model quality...
06/30/2020 ∙ by Dmitry Lepikhin, et al. ∙
7
∙
share
read it
-
Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
Lingvo is a Tensorflow framework offering a complete solution for collab...
02/21/2019 ∙ by Jonathan Shen, et al. ∙
13
∙
share
read it
-
GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism
GPipe is a scalable pipeline parallelism library that enables learning o...
11/16/2018 ∙ by Yanping Huang, et al. ∙
0
∙
share
read it
-
Regularized Evolution for Image Classifier Architecture Search
The effort devoted to hand-crafting image classifiers has motivated the ...
02/05/2018 ∙ by Esteban Real, et al. ∙
0
∙
share
read it
-
Learning Efficient Representations for Reinforcement Learning
Markov decision processes (MDPs) are a well studied framework for solvin...
08/28/2015 ∙ by Yanping Huang, et al. ∙
0
∙
share
read it
-
Partitioning Large Scale Deep Belief Networks Using Dropout
Deep learning methods have shown great promise in many practical applica...
08/28/2015 ∙ by Yanping Huang, et al. ∙
0
∙
share
read it
